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

    Neuronpedia

    INDEX
    Explanations

    descriptions of personal experiences and stories related to various topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.42
    /***
    -1.12
    ⓧ
    -1.07
    /**
    -0.92
    
    -0.91
    /*
    -0.88
    <?
    -0.84
    <?
    -0.83
    //};
    -0.75
    ///**
    -0.70
    POSITIVE LOGITS
     maneu
    1.06
     épu
    0.99
     vété
    0.96
     maroc
    0.94
     fameux
    0.93
     héro
    0.91
     curieux
    0.87
     eiffel
    0.86
     milano
    0.86
     And
    0.86
    Act Density 0.348%

    No Known Activations