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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section and identify contextual transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âgées
    -0.77
     Balboa
    -0.75
    GRAPH
    -0.69
     africains
    -0.69
     AAS
    -0.68
     Calvo
    -0.67
     Mesozoic
    -0.67
     răm
    -0.67
     paille
    -0.67
     peint
    -0.65
    POSITIVE LOGITS
     INTO
    1.65
     Into
    1.61
    Into
    1.57
     into
    1.50
    INTO
    1.37
    into
    1.16
     onto
    0.91
    ")){
    0.90
    _"+
    0.86
    InjectAttribute
    0.86
    Act Density 0.116%

    No Known Activations