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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tp
    -0.73
    eem
    -0.72
    raged
    -0.68
    cess
    -0.68
    eq
    -0.67
    pered
    -0.66
     Urug
    -0.65
    Lt
    -0.65
    edited
    -0.65
    ioned
    -0.65
    POSITIVE LOGITS
     Barron
    1.03
    sonian
    0.87
     Grimm
    0.86
    riages
    0.80
    agy
    0.79
     Webster
    0.76
    astics
    0.76
    agraph
    0.74
     baskets
    0.73
    oké
    0.72
    Act Density 0.011%

    No Known Activations