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

    Neuronpedia

    INDEX
    Explanations

    instances of names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sarah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -1.01
    ebin
    -0.90
    ographed
    -0.83
     nomine
    -0.81
    OWER
    -0.78
    ugal
    -0.74
    chwitz
    -0.72
    ribution
    -0.72
    rosse
    -0.70
    bats
    -0.70
    POSITIVE LOGITS
     Palin
    1.18
     Jane
    0.98
     Connor
    0.97
     Koen
    0.93
     McL
    0.87
     Chal
    0.83
     Michelle
    0.81
     Jessica
    0.79
     Kate
    0.76
     Huckabee
    0.76
    Act Density 0.010%

    No Known Activations