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

    Neuronpedia

    INDEX
    Explanations

    professional terms or titles related to specific fields

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.12
    //---
    -0.76
    /***
    -0.73
    public
    -0.71
    SourceChecksum
    -0.70
    <?
    -0.66
    /*---
    -0.65
    ⓧ
    -0.64
    /***
    -0.64
    /*!
    -0.64
    POSITIVE LOGITS
     increa
    1.59
     Minang
    1.54
     disagre
    1.53
     unlaw
    1.50
     affor
    1.50
     thut
    1.50
     maneu
    1.49
     gaily
    1.48
     jaya
    1.47
     unwarran
    1.44
    Act Density 0.091%

    No Known Activations