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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name Baldwin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Drug
    -0.70
    ple
    -0.69
    itia
    -0.69
    Terror
    -0.68
    MER
    -0.65
    PUT
    -0.65
    aciously
    -0.65
    ULE
    -0.63
    patient
    -0.63
    ocrine
    -0.63
    POSITIVE LOGITS
     Baldwin
    1.41
     Osw
    1.04
     Seym
    0.80
    mpeg
    0.80
    halla
    0.77
    jug
    0.77
    ©¶æ¥µ
    0.75
     Advantage
    0.72
    rities
    0.71
    racuse
    0.71
    Act Density 0.008%

    No Known Activations