Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to figures and diagrams in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.51
    SourceChecksum
    -0.50
     createState
    -0.49
     CreateTagHelper
    -0.45
    hagen
    -0.44
     &___
    -0.44
    קרי
    -0.43
    TabIndex
    -0.43
    argout
    -0.42
    seth
    -0.42
    POSITIVE LOGITS
     diagrams
    1.07
     diagram
    1.02
     schematic
    0.91
     Schematic
    0.88
     Diagrams
    0.86
     Diagram
    0.86
     DIAGRAM
    0.85
    CloseOperation
    0.84
     illustrations
    0.79
     diagrama
    0.78
    Act Density 0.557%

    No Known Activations