method
active
method:behavior-manifold-fitting-m-ybehavior manifold fitting (M_y)
Method to fit a manifold M_y to output probability distributions.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Central framework: steering neural networks by intervening along the curved manifold where a concept lives, rather than in straight lines through activation space.
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.
- Manifold fitted to output probability distributions (behavior).
- The procedure of fitting a one-dimensional manifold (path) to clusters in activation or behavior space to capture the geometric structure of a concept.
- Method to fit a manifold M_h to neural representations in activation space.
- Method that optimizes activation interventions so that resulting behaviors trace M_y, recovering activation paths that follow M_h curvature.
- One-dimensional curved surface in output probability space; the paper shows this mirrors representation manifold structure.
- Central empirical result showing causal coupling between representation and behavior geometry across multiple substrates and modalities.
- Generalization finding from the full paper extending beyond days-of-week to other structured concepts.