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

    Neuronpedia

    INDEX
    Explanations

    official terms or designations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.50
    
    -0.80
    ⓧ
    -0.77
    /***
    -0.77
    /*++
    -0.69
    /*
    -0.69
    /**
    -0.69
    ///**
    -0.66
    <?
    -0.66
    }{||
    -0.66
    POSITIVE LOGITS
     official
    1.96
     Official
    1.93
    Official
    1.82
     OFFICIAL
    1.78
    official
    1.74
     affor
    1.60
     maneu
    1.56
     Officially
    1.55
    OFFICIAL
    1.51
     Juf
    1.47
    Act Density 0.128%

    No Known Activations