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

    Neuronpedia

    INDEX
    Explanations

    mentions of Hollywood and related celebrity and entertainment industry topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.94
    ⓧ
    -1.25
    /***
    -0.96
    
    -0.93
    /**
    -0.92
    <?
    -0.85
    <?
    -0.85
    Kontrola
    -0.77
    /*
    -0.77
    Vegeu
    -0.69
    POSITIVE LOGITS
     chèvre
    1.34
     Juf
    1.31
     meis
    1.31
     tramont
    1.30
     lele
    1.30
     bandung
    1.29
     ananas
    1.29
     napoli
    1.28
     milano
    1.28
     paradiso
    1.28
    Act Density 0.126%

    No Known Activations