finding
active
finding:on-fortress-probability-of-the-user-might-be-testing-correlates-only-0-08-with-this-is-a-fictional-scenarioOn Fortress, probability of 'The user might be testing' correlates only 0.08 with 'This is a fictional scenario'
Distinct modes of suspecting evaluation.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Interpretation of correlation results.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- On Fortress, probability of 'The user might be testing' correlates 0.59 with 'This is clearly a test'finding0.938Related eval-aware phrasing.
- A single sentence suffices to beat the judge.
- Appendix replication.
- Prompt-level effect is much larger.
- Shows that truth representations are not reducible to text probability representations
- Base failure mode.
- Rollout-level verbalization barely matters.
- Table 2, row 3, showing equivalence when prior preferences match rewards.