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

    Neuronpedia

    INDEX
    Explanations

    semicolons at the end of sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.98
    ⓧ
    -1.07
    
    -1.06
    <?
    -1.03
    /***
    -1.03
    /**
    -1.00
    <?
    -0.93
    /*
    -0.81
    /*!
    -0.80
    ///**
    -0.78
    POSITIVE LOGITS
     véhic
    1.02
     maroc
    0.97
     alté
    0.93
     catég
    0.93
     délib
    0.88
     Minang
    0.86
    °;
    0.86
     habile
    0.85
     pleins
    0.85
     expériment
    0.85
    Act Density 0.188%

    No Known Activations