hypothesis
active
hypothesis:if-j-space-is-workspace-like-instructions-to-hold-a-concept-in-mind-will-activate-the-corresponding-j-lens-vectors-independent-of-outputIf J-space is workspace-like, instructions to hold a concept in mind will activate the corresponding J-lens vectors independent of output.
Directed modulation prediction.
Source paper
extracted_fromAuthors
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (3)
finding
- Hidden computation.
- No-instruction baseline rate of target in J-lens is approximately zero across task families.supportsModulation control.
- Directed modulation.
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.
- Structural signature.
- The J-space can hold more concepts when they have coherent relationships than unrelated ones.hypothesis0.833Tested with lists.
- Does J-space competition mirror the sharp competitive ignition of the brain's workspace?question0.827Unresolved.
- Mediation control.
- Imagine instruction raises property name in J-lens while J-orthogonalized property probe stays at baseline.finding0.819J-space privileged.
- Limitation.
- Decomposition result.
- Selectivity.