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

    Neuronpedia

    INDEX
    Explanations

    updates and announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.43
    ⓧ
    -1.07
    <?
    -0.91
    /***
    -0.79
    /**
    -0.74
    /*
    -0.74
    
    -0.72
    <?
    -0.61
    /*++
    -0.60
    Література
    -0.59
    POSITIVE LOGITS
     wien
    1.77
     lele
    1.77
     bayern
    1.57
     meis
    1.56
     maneu
    1.55
     dises
    1.55
     ohr
    1.51
     bandung
    1.49
     ananas
    1.49
     kram
    1.48
    Act Density 0.108%

    No Known Activations