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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical information related to physics and engineering

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ername
    -0.82
    edy
    -0.79
    nis
    -0.77
    center
    -0.77
    oult
    -0.71
    ĸļ
    -0.71
    advertising
    -0.69
    Ń·
    -0.69
    avascript
    -0.67
    olulu
    -0.67
    POSITIVE LOGITS
     each
    1.01
     these
    0.84
     incoming
    0.83
     goods
    0.81
     existing
    0.76
     computation
    0.76
     occurrence
    0.76
     extant
    0.75
     permissible
    0.73
     individual
    0.73
    Act Density 1.017%

    No Known Activations