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

    Neuronpedia

    INDEX
    Explanations

    phrases related to terms that are 'widely' known or performed

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.19
    
    -0.97
    <?
    -0.96
    /**
    -0.72
    <?
    -0.69
    ⓧ
    -0.64
    /*
    -0.64
     don
    -0.63
    <!--
    -0.62
    /***
    -0.61
    POSITIVE LOGITS
     Widely
    1.85
     widely
    1.85
     stockholm
    1.64
     affor
    1.59
     accla
    1.57
     increa
    1.53
     nece
    1.46
     squa
    1.45
     madonna
    1.43
     fta
    1.42
    Act Density 0.050%

    No Known Activations