claim
active
claim:robust-interpretability-tools-require-inductive-biases-that-match-the-data

Robust interpretability tools require inductive biases that match the data.

Overall conclusion.

Source paper

extracted_from
Priors in Time: Missing Inductive Biases for Language Model Interpretability
(2025) · Lubana, Ekdeep Singh · Rager, Can · Hindupur, Sai Sumedh R. · Costa, Valerie +12

Neighborhood — ranked by edge-count