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

    Neuronpedia

    INDEX
    Explanations

    the word "purely"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.33
    <?
    -1.07
    /***
    -0.98
    <?
    -0.97
    
    -0.92
    ⓧ
    -0.92
    /*!
    -0.85
    /**
    -0.79
    ///**
    -0.75
    //});
    -0.71
    POSITIVE LOGITS
     strick
    1.59
     impra
    1.53
     affor
    1.52
     Mainly
    1.42
     ecru
    1.41
     purely
    1.40
     excru
    1.39
    Mainly
    1.37
     accla
    1.36
     Primarily
    1.36
    Act Density 0.055%

    No Known Activations