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

    Neuronpedia

    INDEX
    Explanations

    times expressed as 24-hour clock notation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number six in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.66
    imaru
    -0.66
    rolet
    -0.66
    atem
    -0.62
    ilic
    -0.60
    ãĥ¼ãĥ³
    -0.57
    ãĥ¼ãĥĨ
    -0.57
    recogn
    -0.56
    qqa
    -0.54
    urus
    -0.54
    POSITIVE LOGITS
    th
    0.90
    ½
    0.80
    teenth
    0.76
    ï¸ı
    0.72
    °
    0.72
    %"
    0.71
    %-
    0.70
     months
    0.69
     ½
    0.67
    TH
    0.65
    Act Density 0.460%

    No Known Activations