finding
active
finding:logit-lens-decodes-probe-directions-to-cheating-illicit-dishonest-tokens-though-absent-from-synthetic-data

Logit lens decodes probe directions to cheating/illicit/dishonest tokens though absent from synthetic data

Probes encode cheating concept.

Source paper

extracted_from
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
(2026) · Leon Bergen · Usha Bhalla · Andrew Lee · Barak Widawsky +14

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.