Behavior Space

A geometric space of all output token probability distributions, equipped with Hellinger distance, used to visualize model behavior.

Neighborhood — ranked by edge-count

method

Hellinger distance
uses
Metric used to define geometric space of output token probability distributions in behavior manifold analysis.

concept

Behavioral Null Space
related_to
The span of vector directions that do not change network behavior; a key concept distinguishing MAS from model stitching.
behavior manifold
associated_with
One-dimensional curved surface in output probability space; the paper shows this mirrors representation manifold structure.

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.

3D behavioral spaceconcept0.844
The traditional space of movement in the physical world where animals exhibit problem-solving behavior.
Behaviorally Binary Subspaceconcept0.801
A vector subspace that causally impacts outputs only through the sign of its values, enabling harmless magnitude divergence
Configuration Spaceconcept0.796
The ensemble of all possible configurations of a building, including incomplete states and paths between them.
Activation spaceconcept0.792
Representation space on which linear probes operate to attribute harmful behaviors to training data.
Manifold Fitting to Representation/Behavior Spacemethod0.787
The procedure of fitting a one-dimensional manifold (path) to clusters in activation or behavior space to capture the geometric structure of a concept.
How Does Evolution Search The Space Of Behaviorshapingquestion0.776
Problem Space Frameworkframework0.774
Behavior-based Pathconcept0.766
The path in activation space derived by optimizing steering interventions to produce outputs along the behavior manifold, independent of representation geometry.