Sentence polarity

Whether a statement is affirmative or negated; a surface feature that confounds early-layer truth probes.

Neighborhood — ranked by edge-count

concept

Polarity-dependent truth direction (tP)
associated_with
A direction that classifies affirmative statements effectively but inverts for negated variants, dominating in early layers.

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.

linearityconcept0.729
The sequential, continuous order of text, often challenged by diagrammatic branching.
Selectivitymethod0.713
Adapted control task metric measuring difference between odds-ratio on original task and arbitrary-label control task
Practicalityconcept0.710
The directness of motivation by practical concerns, characteristic of living processes in the examples.
Nonlinearityconcept0.707
Negative polarity item licensingconcept0.699
Linguistic phenomenon where NPI lexemes like 'any' require negative-polarity sentential contexts; studied as case study in CausalGym
What class of sentences to allow as expressing various kinds of commitments?question0.694
Open problem on the expressiveness of commitment sentences.
abnormalityconcept0.691
EEG abnormality concept (e.g., epileptiform activity) used to interpret SAE features.
Modularityconcept0.689
Property of developmental systems where functions are encapsulated in modules with simple triggers, enhancing evolvability.