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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and capitalized words

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.91
    abwe
    -0.81
    perty
    -0.80
    omever
    -0.73
    selves
    -0.72
    ĸļ
    -0.66
    åĮ
    -0.65
    thood
    -0.65
     compe
    -0.63
    DonaldTrump
    -0.62
    POSITIVE LOGITS
     Incident
    0.72
     Handbook
    0.70
     Tribune
    0.69
     Gazette
    0.68
     Difference
    0.67
    osphere
    0.66
     Tribunal
    0.65
     Files
    0.65
     Report
    0.65
     Plan
    0.65
    Act Density 0.289%

    No Known Activations