finding
active
finding:planned-word-features-were-found-in-about-half-of-the-poems-investigatedPlanned word features were found in about half of the poems investigated.
May reflect CLT gaps or non-planning.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Planning in poems.
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.
- Planned words are represented by ordinary word features rather than planning-specific features.claim0.837Model thinks about planned words like read words.
- Quantitative planning intervention result.
- Judge sensitivity.
- Tested via interventions at the newline planning site.
- Decoder cosine similarity maps onto concept similarity.
- Feature presence depends on concept frequency in training data, with a threshold scaling inversely with alive features.
- features serve as oversight signals to intentionally design models with desirable capabilitiesquote0.736Core vision statement.
- All models exhibit above-baseline representation of the think word when instructed to think about itfinding0.736In the intentional control experiment, all tested models show above-zero cosine similarity to the think word's concept vector.