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

    Neuronpedia

    INDEX
    Explanations

    simple answers or statements

    oai_token-act-pair · gpt-3.5-turbo

    the term "simple" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.80
    raints
    -0.78
    vance
    -0.74
    hips
    -0.73
     extensively
    -0.71
    ingle
    -0.68
    igham
    -0.68
     vigorously
    -0.68
    inburgh
    -0.66
    hovah
    -0.65
    POSITIVE LOGITS
    tons
    1.25
    minded
    0.97
    wallet
    0.94
    ton
    0.85
     arithmetic
    0.83
    json
    0.82
    ified
    0.80
     syrup
    0.79
     minded
    0.79
    ured
    0.77
    Act Density 0.029%

    No Known Activations