behavior manifold M_y

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• behavior manifold fitting (M_y)method0.904
  Method to fit a manifold M_y to output probability distributions.
• optimization of interventions to follow behavior manifold M_ymethod0.831
  Method that optimizes activation interventions so that resulting behaviors trace M_y, recovering activation paths that follow M_h curvature.
• Manifold Fitting to Representation/Behavior Spacemethod0.810
  The procedure of fitting a one-dimensional manifold (path) to clusters in activation or behavior space to capture the geometric structure of a concept.
• Activation manifolds and behavior manifolds are approximately isometric across cyclic and sequential concepts.claim0.792
• Activation-Behavior Manifold Isometryconcept0.791
• Interventions along activation manifold M_h yield behavioral trajectories following behavior manifold M_y, and vice versa — bidirectional relationship demonstrated across language models and video world models.finding0.789
  Central empirical result showing causal coupling between representation and behavior geometry across multiple substrates and modalities.
• Analogous alignment between representation manifold and behavior manifold is found across months, letters, ages, and synthetic in-context learning tasks in language models.finding0.770
  Generalization finding from the full paper extending beyond days-of-week to other structured concepts.
• Behavior Spaceconcept0.765
  A geometric space of all output token probability distributions, equipped with Hellinger distance, used to visualize model behavior.