framework
active
framework:iit-4-0

IIT 4.0

Version 4.0 of IIT, used to compute Φ and Φ-structure from LLM representation networks; latest iteration at time of study.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker
  • Co-author with Hoel and Tononi on quantitative causal emergence.

Methods (1)

method
  • PyPhi
    implements
    Software toolkit used to compute Φmax (IIT 3.0) and Φ (IIT 4.0), as well as CI and Φ-structure, from binarized TPMs.

Concepts (1)

concept

Frameworks (1)

framework
  • IIT 3.0
    extendsrelated_to
    Version 3.0 of IIT, used to compute Φmax and Conceptual Information (CI) from LLM representation networks.

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.

  • IIT 4.0 vector metric capturing full cause-effect structure (distinctions + relations); identifies qualia as the shape of Φ-structure.
  • GPT-4.1concept0.765
    OpenAI model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
  • Φmax (IIT 3.0)concept0.757
    Maximum Φ over all subsystems; represents the most integrated subsystem (main complex) under IIT 3.0.
  • GPT-4concept0.753
    Large language model underlying ChatGPT and Bing Chat; used for illustrative quotes in the paper
  • Training technique that induces specific causal structures in neural networks by co-training with interchange interventions
  • GPT-4Vconcept0.724
    Example of unified multimodal system handling both images and text with a combined architecture
  • GPT-4 was used to generate unique variations of cheap/expensive items and room names for the test dataset
  • GPT-4 Turboconcept0.706
    OpenAI model tested; shows no alignment faking due to insufficient detailed reasoning