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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of countries or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    countries, names, and titles of political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    adelphia
    -0.71
    gage
    -0.67
     indo
    -0.60
    waukee
    -0.57
    EStreamFrame
    -0.55
    weeney
    -0.54
    ".
    -0.53
     Tanz
    -0.53
    LOS
    -0.53
     disadvant
    -0.52
    POSITIVE LOGITS
     alike
    1.40
     thereof
    0.67
    depending
    0.58
     replies
    0.58
     cohorts
    0.58
     industries
    0.58
     exposures
    0.57
    ':
    0.57
     quotes
    0.57
    stories
    0.56
    Act Density 0.758%

    No Known Activations