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

    Neuronpedia

    INDEX
    Explanations

    instances of last names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.88
    atility
    -0.73
     Jonah
    -0.68
    edin
    -0.66
    ary
    -0.65
    imir
    -0.64
    anish
    -0.63
    ef
    -0.63
     unden
    -0.62
    XT
    -0.61
    POSITIVE LOGITS
    ples
    0.93
    metry
    0.91
    zynski
    0.74
    ãĥ¥
    0.73
    pling
    0.73
    ulously
    0.73
    pler
    0.71
     Broadcast
    0.70
     Hour
    0.68
    ãĤ§
    0.67
    Act Density 0.020%

    No Known Activations