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

    Neuronpedia

    INDEX
    Explanations

    negative mathematical values or signs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.55
     estekak
    -0.54
     Ele
    -0.50
    Ele
    -0.50
    SharedCtor
    -0.47
     mev
    -0.46
     <
    -0.46
    twimg
    -0.45
    TextHelper
    -0.45
    PointerException
    -0.44
    POSITIVE LOGITS
    出版年
    0.66
     Vikipedi
    0.65
    $")
    0.60
     onCreateView
    0.60
    fortawesome
    0.60
    EndContext
    0.58
     purtroppo
    0.58
    følgelig
    0.58
    %")
    0.57
    TAWA
    0.57
    Act Density 0.055%

    No Known Activations