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

    Neuronpedia

    INDEX
    Explanations

    statements expressing personal beliefs or opinions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    endpush
    -0.87
    IsContent
    -0.84
     houſe
    -0.81
     purpoſe
    -0.80
     متعلقه
    -0.79
     Chriftian
    -0.79
     transférez
    -0.77
     مرئيه
    -0.75
    =$?
    -0.74
     leaſt
    -0.74
    POSITIVE LOGITS
     ModelExpression
    0.58
    defineProperty
    0.51
     beant
    0.36
    isi
    0.35
    балан
    0.35
     les
    0.34
     bien
    0.33
     fieldNum
    0.33
     conse
    0.33
    /***/
    0.32
    Act Density 0.181%

    No Known Activations