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

    Neuronpedia

    INDEX
    Explanations

    legal and legislative references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.02
    ⓧ
    -0.98
    /**
    -0.93
    
    -0.84
    <?
    -0.82
    <?
    -0.76
    SourceChecksum
    -0.71
    fputs
    -0.60
    PerformLayout
    -0.58
    rmdir
    -0.57
    POSITIVE LOGITS
     maroc
    0.98
     vasi
    0.92
     jaya
    0.90
     kasa
    0.90
     kac
    0.90
     riva
    0.90
     kaos
    0.88
     lele
    0.87
     saha
    0.86
     torba
    0.86
    Act Density 0.247%

    No Known Activations