finding
active
finding:small-to-large-edges-in-the-french-antonym-prompt-are-mediated-by-a-limited-set-of-heads-using-key-side-opposite-requested-adjective-features-and-query-side-antonym-featuresSmall-to-large edges in the French antonym prompt are mediated by a limited set of heads using key-side opposite-requested/adjective features and query-side antonym features
QK attribution of antonym heads.
Source paper
extracted_fromNeighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Antonym interpretation.
Hypotheses (1)
hypothesis
- Prior hypothesis not confirmed.
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.
- Steering validation for antonym mechanism.
- Operation component is language-independent.
- Implicit modulation.
- Perturbation validation.
- Motivation.
- Swapping small-size features for hot-temperature features yields language-appropriate antonyms of hot.finding0.765Operand circuitry is language-agnostic.
- Control experiment ruling out token-count as the cause of truth geometry shifts.
- Suggestive evidence for language-independent truth representation in LLMs