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

    Neuronpedia

    INDEX
    Explanations

    names of personalities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uously
    -0.69
    ulhu
    -0.64
     Marketable
    -0.64
     Fancy
    -0.64
     depend
    -0.63
    terday
    -0.63
     FANTASY
    -0.62
    ruary
    -0.61
    raped
    -0.60
    CW
    -0.59
    POSITIVE LOGITS
    zen
    0.80
    onson
    0.79
    uner
    0.78
    ãĤ±
    0.77
    ĸļ
    0.75
    ensen
    0.75
    etus
    0.75
    enberg
    0.73
    ogle
    0.71
    enhagen
    0.70
    Act Density 16.397%

    No Known Activations