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

    Neuronpedia

    INDEX
    Explanations

    specific parts or components specified in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.17
    /***
    -0.81
     eliminate
    -0.66
    /*!
    -0.65
    <?
    -0.63
    ///**
    -0.63
    /*
    -0.63
    
    -0.63
     consolidate
    -0.61
    ⓧ
    -0.60
    POSITIVE LOGITS
     stockholm
    1.14
     lidl
    1.10
     mef
    1.10
     aen
    1.09
     Parts
    1.04
     prétend
    1.03
     maroc
    1.03
     wien
    1.03
     lele
    1.02
     catég
    1.02
    Act Density 0.122%

    No Known Activations