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

    Neuronpedia

    INDEX
    Explanations

    references to a particular time or repetition of actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.01
    /***
    -0.76
    ⓧ
    -0.69
    
    -0.68
    ///**
    -0.67
    <?
    -0.67
    /*!
    -0.64
     дописавши
    -0.61
    <?
    -0.61
    export
    -0.61
    POSITIVE LOGITS
     jaya
    1.43
     kram
    1.41
     wien
    1.39
     stockholm
    1.35
     lele
    1.33
     haup
    1.28
     unce
    1.27
     seksi
    1.26
     frankfurt
    1.26
     kasa
    1.26
    Act Density 0.089%

    No Known Activations