thinker

active

thinker:ilharco-et-al

Ilharco et al.

Cited for activation patching method for supervised steering vector derivation

Authored

0

Introduces

0

Studies

0

Affiliations

0

Cited by

0

More papers — OpenAlex / S2

Other inbound relations (1)

citesWhen Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models(paper)

Recent mentions (1)

papers-typed
wang-2025-thinking-llms.md