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

    Neuronpedia

    INDEX
    Explanations

    words related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
    ully
    -0.78
    ighed
    -0.75
    aline
    -0.72
    ebook
    -0.68
    entimes
    -0.68
    cca
    -0.67
     Chamberlain
    -0.67
    ldom
    -0.67
    ften
    -0.66
    POSITIVE LOGITS
     avenues
    0.82
     examples
    0.81
     iterations
    0.81
     categories
    0.78
     paragraphs
    0.78
     strokes
    0.77
     victories
    0.77
     deviations
    0.77
     facts
    0.77
     ingredients
    0.76
    Act Density 0.288%

    No Known Activations