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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Downs
    -0.77
     suites
    -0.72
     Architects
    -0.70
     grid
    -0.69
     Capitalism
    -0.66
     Caps
    -0.66
     Farms
    -0.65
     districts
    -0.65
     ACTION
    -0.64
     SOC
    -0.64
    POSITIVE LOGITS
    zzy
    1.10
    iona
    0.99
    annah
    0.97
    Jenn
    0.97
    abeth
    0.95
    anie
    0.94
    atalie
    0.94
    ileen
    0.94
    amus
    0.93
    ilyn
    0.93
    Act Density 0.164%

    No Known Activations