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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    the repeated appearance of the syllable "ha", indicating a focus on humor or laughter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atories
    -0.83
    papers
    -0.83
    rations
    -0.75
    URES
    -0.68
    toc
    -0.67
     Cosponsors
    -0.65
    tle
    -0.65
    ãĤ±
    -0.63
    rats
    -0.63
     largeDownload
    -0.63
    POSITIVE LOGITS
    wn
    1.14
    user
    0.97
    pless
    0.93
    iku
    0.90
    pton
    0.89
    ffe
    0.88
    ichi
    0.85
    pta
    0.85
    ugh
    0.84
    ild
    0.84
    Act Density 0.011%

    No Known Activations