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

    Neuronpedia

    INDEX
    Explanations

    quantities or measurements mentioned in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.55
    ⓧ
    -1.16
    
    -1.00
    /**
    -0.98
    /*
    -0.89
    /***
    -0.88
    /*++
    -0.81
     rehabilitate
    -0.78
    <?
    -0.78
    ///**
    -0.74
    POSITIVE LOGITS
     jawa
    1.41
     lele
    1.38
     bandung
    1.36
     maroc
    1.31
     kaos
    1.28
     riva
    1.27
     Minang
    1.27
     kac
    1.25
     kase
    1.22
     thuy
    1.22
    Act Density 0.068%

    No Known Activations