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

    Neuronpedia

    INDEX
    Explanations

    URLs or web addresses in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     useAppContext
    -0.86
    IsContent
    -0.81
    bitat
    -0.79
     betweenstory
    -0.75
     ErrIntOverflow
    -0.73
    HtmlAttribute
    -0.72
    //
    -0.71
    קישורים
    -0.71
    ]='\
    -0.71
     XXXV
    -0.69
    POSITIVE LOGITS
     I
    0.47
    <eos>
    0.45
    tops
    0.45
    ilim
    0.41
    rame
    0.41
     top
    0.41
     postes
    0.39
     Hall
    0.39
     lui
    0.39
    мені
    0.38
    Act Density 0.011%

    No Known Activations