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

    Neuronpedia

    INDEX
    Explanations

    descriptive words related to creativity and artistry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.38
    ⓧ
    -0.78
    /**
    -0.77
    ,
    -0.76
     also
    -0.74
    <?
    -0.73
    
    -0.73
    displayquote
    -0.73
    itemize
    -0.72
    </tbody>
    -0.71
    POSITIVE LOGITS
     increa
    2.26
     maneu
    2.23
     affor
    2.16
     impra
    2.10
     accla
    1.97
     strick
    1.96
     disagre
    1.96
     fta
    1.95
     stockholm
    1.95
     ftu
    1.94
    Act Density 0.167%

    No Known Activations