mechanistic interpretability

Mechanistic interpretability is a subfield of research within explainable artificial intelligence that aims to understand the internal workings of neural networks by analyzing the mechanisms present in their computations. The approach seeks to analyze neural networks in a manner similar to how binar

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.