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

    Neuronpedia

    INDEX
    Explanations

    phrases related to encouragement or emphasis on a particular aspect

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.45
    <!--
    -0.88
    /***
    -0.86
    ///**
    -0.80
    /*!
    -0.79
    /**
    -0.77
    <?
    -0.72
    
    -0.71
    /*
    -0.68
    glColor
    -0.66
    POSITIVE LOGITS
     ecru
    1.71
     maneu
    1.48
     impra
    1.45
     bordeaux
    1.44
     !...
    1.44
     increa
    1.42
     accla
    1.42
     swarovski
    1.41
     ?...
    1.41
     affor
    1.40
    Act Density 0.115%

    No Known Activations