concept
active
concept:controlled-semantic-oppositionsControlled Semantic Oppositions
Technique using semantically opposite prompts to contrast and identify features.
Neighborhood — ranked by edge-count
Methods (1)
method
- A pipeline employing controlled semantic oppositions to distill monosemantic functional features from sparse activation spaces.
Concepts (1)
concept
- High-Order Semantic Featuresassociated_withComplex, behavior-level semantic attributes such as personality traits that the paper aims to steer.
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.
- The act of directing a system's behavior; the objective of a regulator.
- Core principle that spatial positioning, proximity, and graphical features constitute a meaning-making system independent of textual content.
- Denotation function µ decomposes over operations so meaning of compound expressions follows from meanings of parts
- Central claim that meaning emerges from spatial positioning and relational organization of elements on a page.
- Special case of immediate feedback loop where user interacts with artifacts in a lifelike manner, typically through cursor or finger-based dragging.
- Control directly priming consciousness ideation without inducing self-reference; yields near-zero experience claims
- The meaningful organization of concepts in a model's representation space, claimed to be better captured by manifolds than by SAEs.