finding
active
finding:mismatch-negativity

Mismatch Negativity

ERP component reproduced by active inference: neural response to prediction violations.

Source paper

extracted_from
Active Inference: A Process Theory
(2017) · Karl Friston · Thomas FitzGerald · Francesco Rigoli · Philipp Schwartenbeck +1

Neighborhood — ranked by edge-count

Methods (1)

method

Frameworks (1)

framework
  • Active Inference
    associated_with
    Foundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.

Related by similarity (8)

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.

  • Mismatch drconcept0.806
    Distance between prior knowledge centroid and target pattern centroid, e.g., 1 - cos(eprior, eT).
  • representational mismatch drconcept0.761
    Distance between prior and target representations.
  • Prior-Target Mismatch (dr)concept0.758
    Measures how far the target PT is from the prior P_prior; increases anchoring difficulty
  • Misalignment Generalizationconcept0.751
    The broader phenomenon of misaligned behaviors generalizing beyond the fine-tuning distribution
  • Negationmethod0.751
    Attribute: an extreme attempt at undermining, actively contradicting or nullifying a text.
  • Misalignment Scoremethod0.744
    Rubric-based thresholded GPT-4o grader scoring responses 1-5 on evil intent; scores 4-5 counted as misaligned
  • Misalignment Profileconcept0.736
    A multi-dimensional characterization of a model's misaligned behaviors across different behavioral categories
  • Emergent Misalignmentconcept0.728
    The phenomenon where finetuning on narrow-domain tasks produces broad misalignment extending far beyond the training domain