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

    Neuronpedia

    INDEX
    Explanations

    statements or discussions about various accomplishments and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.40
    ⓧ
    -1.52
    /**
    -1.46
    <?
    -1.28
    
    -1.19
    /*
    -1.06
    /***
    -0.91
    ///**
    -0.85
    <?
    -0.83
    #![
    -0.82
    POSITIVE LOGITS
     lele
    1.21
     maroc
    1.00
     seksi
    0.98
     bandung
    0.97
     jawa
    0.95
     roul
    0.94
     thuy
    0.93
    tawan
    0.93
     optik
    0.93
     moza
    0.92
    Act Density 0.157%

    No Known Activations