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

    Neuronpedia

    INDEX
    Explanations

    mentions of technology, data management, and political issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     silikon
    -1.08
     kafe
    -1.06
     karton
    -0.97
     keramik
    -0.95
     seksi
    -0.93
     optik
    -0.92
     Meksi
    -0.92
     mikrofon
    -0.89
     viendra
    -0.88
    <bos>
    -0.86
    POSITIVE LOGITS
     ecru
    0.75
     notoriously
    0.72
     generally
    0.71
     often
    0.70
     usually
    0.69
     inherently
    0.69
     currently
    0.67
     typically
    0.67
     comprised
    0.67
     itemList
    0.66
    Act Density 0.449%

    No Known Activations