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

    Neuronpedia

    INDEX
    Explanations

    references to questions and answers related to technical information, specifically in a structured format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.26
    
    -0.95
    /*
    -0.93
    ⓧ
    -0.88
    /**
    -0.82
    <?
    -0.73
    //
    -0.67
    ///**
    -0.66
    HasIndex
    -0.64
    DeleteMapping
    -0.64
    POSITIVE LOGITS
     maneu
    1.85
     affor
    1.55
     Juf
    1.49
     erad
    1.43
     increa
    1.41
     shenan
    1.40
     Minang
    1.39
     fortn
    1.37
     wien
    1.37
     reluct
    1.37
    Act Density 0.085%

    No Known Activations