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

    Neuronpedia

    INDEX
    Explanations

    references to news articles or reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.73
    bably
    -0.70
    zzle
    -0.68
    antly
    -0.68
    lets
    -0.67
     Scand
    -0.66
    ttes
    -0.65
     vain
    -0.61
     Ernst
    -0.61
    ceivable
    -0.61
    POSITIVE LOGITS
    AAF
    1.14
    GS
    1.12
    ADA
    1.03
     Embassy
    1.03
    MC
    0.97
     embassy
    0.95
    $
    0.94
    GA
    0.94
     Airways
    0.91
     Dollar
    0.91
    Act Density 0.048%

    No Known Activations