Paper Citation Record · LEDGER

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

As of 10 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 4 inbound Pith citation observations for arXiv:2506.05166.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.05166 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:29:45.002961Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T10:04:06.753097Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-14T21:18:00.318407Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy17
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3772aed2-6acb-4a08-a69c-7a524d6ca671 · outbound

This paper cites online" 'onlinestring :=.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.768165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06ece96-14c5-464e-834d-dc7ad7b63282 · outbound

This paper cites write newline.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.778131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a7a4ba-b128-4fe7-9ec3-41d8d5ca2ab9 · outbound

This paper cites write newline.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective write newline

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.786484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcfed349-23e6-4ade-af55-189c39c41452 · outbound

This paper cites Stubbersfield.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Stubbersfield

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.577242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ec4dd6b9-8fdc-4074-b803-81dd46760915 · outbound

This paper cites Science in the age of large language models.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Science in the age of large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.561584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a5cd9e91-6d6b-45aa-9955-547dceb2b4b0 · outbound

This paper cites Quantifying and Reducing Stereotypes in Word Embeddings.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Quantifying and Reducing Stereotypes in Word Embeddings

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.807248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efc5a07e-07a5-4a00-aa93-730a8a3a21fd · outbound

This paper cites Man is to computer programmer as woman is to homemaker? debiasing word embeddings.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Man is to computer programmer as woman is to homemaker? debiasing word embeddings

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.546048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a4c7aba8-cf3a-4836-ba85-db936d2ed7c8 · outbound

This paper cites Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.819483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b4416e2-4e1f-4970-a8e2-a74e81159d52 · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Towards automated circuit discovery for mechanistic interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.827250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ee3a01-cf46-4cfe-ae0f-d8639c625ca7 · outbound

This paper cites Gallegos, Ryan A.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Gallegos, Ryan A

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.520197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 358dd5c8-2a99-49ff-879c-add0019436fa · outbound

This paper cites Causal abstractions of neural networks.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Causal abstractions of neural networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.841155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e3a3c02-6824-4351-b7b7-f80224012029 · outbound

This paper cites Multimodal neurons in artificial neural networks.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Multimodal neurons in artificial neural networks

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.494054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9b87056f-b8f7-4591-ae43-061283bd12ea · outbound

This paper cites Localizing Model Behavior with Path Patching.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Localizing Model Behavior with Path Patching

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.855872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97959f3a-54bf-4423-9ae8-50f52bc579d7 · outbound

This paper cites C hat GPT based data augmentation for improved parameter-efficient debiasing of LLM s.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective C hat GPT based data augmentation for improved parameter-efficient debiasing of LLM s

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.477923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 78ad67f0-2229-4412-89cb-86380b5dfe33 · outbound

This paper cites distilbert-base-uncased-finetuned-sst-2-english (revision bfdd146), 2022.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective distilbert-base-uncased-finetuned-sst-2-english (revision bfdd146), 2022

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.461355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 16c76e03-68e9-4de1-9c26-09f0ed430230 · outbound

This paper cites Shovon, and Gene Kim.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Shovon, and Gene Kim

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.444004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8a8dcd2-ad11-46bf-af70-bcb691cfda39 · outbound

This paper cites The impact of debiasing on the performance of language models in downstream tasks is underestimated.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective The impact of debiasing on the performance of language models in downstream tasks is underestimated

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.428479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d0f81c75-6dd2-4d9a-9ad1-a456da917fd3 · outbound

This paper cites Backward Lens: Projecting Language Model Gradients into the Vocabulary Space.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Backward Lens: Projecting Language Model Gradients into the Vocabulary Space

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.882463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d12fa1-2227-4053-9c63-9e7738c4a344 · outbound

This paper cites Linear Representations of Political Perspective Emerge in Large Language Models.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Linear Representations of Political Perspective Emerge in Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.887656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b82d85-c601-4faf-8e6c-89115c2f9854 · outbound

This paper cites Gender bias and stereotypes in large language models.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Gender bias and stereotypes in large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.411906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 791accd6-099f-44b4-a176-3cb679e6cb5b · outbound

This paper cites Sparse feature circuits: Discovering and editing interpretable causal graphs in language models.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Sparse feature circuits: Discovering and editing interpretable causal graphs in language models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.395503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bf25f2f4-f439-4c5c-bcda-4c18322f57d3 · outbound

This paper cites Locating and editing factual associations in gpt.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Locating and editing factual associations in gpt

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.904438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66267b2e-0673-442c-8df7-403023597f77 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Progress measures for grokking via mechanistic interpretability

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.911625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc928338-d764-4f8e-b201-698f2db36b69 · outbound

This paper cites Nationality bias in text generation.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Nationality bias in text generation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.369665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5ff7eb45-af62-47df-b791-e1d12b8744d1 · outbound

This paper cites Biases in large language models: Origins, inventory, and discussion.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Biases in large language models: Origins, inventory, and discussion

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.354171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 847c158c-e188-4133-9580-7cf2bc72b50b · outbound

This paper cites Mechanistic interpretability, variables, and the importance of interpretable bases.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Mechanistic interpretability, variables, and the importance of interpretable bases

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.337615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9d893a85-de54-4037-a156-6432b71273b4 · outbound

This paper cites Zoom in: An introduction to circuits.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Zoom in: An introduction to circuits

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.934254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 135a2cb1-9ab0-45a4-b8d0-a2cede383089 · outbound

This paper cites Gender biases in automatic evaluation metrics for image captioning.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Gender biases in automatic evaluation metrics for image captioning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.310828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0cf90f9a-f802-4b7f-a6c8-98685c9a04c0 · outbound

This paper cites Language models are unsupervised multitask learners.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Language models are unsupervised multitask learners

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.948884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7fc6bcb-07b2-4be0-9c34-a6165b7b0261 · outbound

This paper cites Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.953942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fede18b-8b4e-4c08-b56d-f4889fe45dbd · outbound

This paper cites Investigating gender bias in large language models through text generation.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Investigating gender bias in large language models through text generation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.285328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ef6e9eec-cce5-4f92-9452-88191b5a20b1 · outbound

This paper cites Attribution Patching Outperforms Automated Circuit Discovery.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Attribution Patching Outperforms Automated Circuit Discovery

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.964417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb28f1c-b4cf-4562-bbc5-b74d822a9173 · outbound

This paper cites Attribution patching outperforms automated circuit discovery.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Attribution patching outperforms automated circuit discovery

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:45.268077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6d1dcac1-8530-40f4-81a1-002bab812bb4 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.976406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e513610-6d58-4c62-a29b-0ed757fc2a36 · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Investigating gender bias in language models using causal mediation analysis

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.981245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795ad8e5-0f9c-470e-b00f-ec2eff7fd9fe · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.987123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26a9f4e5-0caa-4643-80c8-0ee51cb33f37 · outbound

This paper cites Neural Network Acceptability Judgments.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Neural Network Acceptability Judgments

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.993184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79525a86-b6b0-4a39-b3e9-d08605577f50 · outbound

This paper cites Interpretability at scale: Identifying causal mechanisms in alpaca.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Interpretability at scale: Identifying causal mechanisms in alpaca

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.998131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45d1bd76-2e0c-4611-b48c-608a999fa62a · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:45.002961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6a2ef335-0406-48f7-87ce-ccb2a49563dd · inbound

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability cites this paper.

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T10:04:06.753097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa71bf9e-5315-4636-9005-727082cadf69 · inbound

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations cites this paper.

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-04T09:08:58.465833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75533c7d-b5d6-4745-b05d-4ef1be771b61 · inbound

Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models cites this paper.

Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:18:00.320812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d9d1ab2f-48c3-4301-a161-5a866954f5e9 · inbound

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender cites this paper.

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T04:52:16.728754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.