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

    Neuronpedia

    INDEX
    Explanations

    instructions related to printing documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.22
    ⓧ
    -0.83
    
    -0.77
    <?
    -0.72
    Vegeu
    -0.69
    /**
    -0.67
     springfox
    -0.66
    /*
    -0.63
    /***
    -0.63
    Unmarshaller
    -0.59
    POSITIVE LOGITS
     impra
    1.52
     maneu
    1.46
     affor
    1.45
     increa
    1.41
     emphat
    1.39
     reluct
    1.35
     unspeak
    1.31
     unlaw
    1.31
     exorbit
    1.31
     disagre
    1.30
    Act Density 0.086%

    No Known Activations