Explainable Artificial Intelligence

Broader research program that causal abstraction is presented as a framework for advancing.

Neighborhood — ranked by edge-count

paper

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.

Artificial Intelligenceconcept0.832
Domain where consciousness theories are being applied to synthetic systems; part of broader context of unconventional embodiments.
Artificial General Intelligenceconcept0.775
Target phenomenon; paper seeks unified understanding via world models and life-mind continuity.
Neural Network Interpretabilityconcept0.760
The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper
Non-human intelligenceconcept0.753
Intelligences distinct from human minds, including AI and artificial life agents.
Automated Interpretabilityframework0.749
Method using large language models (Claude) to generate and test explanations of features at scale
Machine Intelligenceconcept0.742
Intelligence realized in a non-organic, technological substrate, potentially free from biological constraints.
Autonomous AI Systemsconcept0.738
Future AI that may be rational, autonomous, and possibly conscious but lack affective consciousness.
How Can We Understand Intelligence In A Wayquestion0.734