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

    Neuronpedia

    INDEX
    Explanations

    the name "Jane" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Jane"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctic
    -0.86
    */(
    -0.84
    orescent
    -0.82
    PDATE
    -0.82
    rophe
    -0.74
    idated
    -0.74
    cffff
    -0.73
    iated
    -0.73
    akespe
    -0.71
    natureconservancy
    -0.70
    POSITIVE LOGITS
     Doe
    1.29
     Jane
    0.92
    Jane
    0.89
     Aust
    0.88
     Jacobs
    0.86
     Roe
    0.81
     Approximately
    0.81
     Seymour
    0.79
     Mayer
    0.79
     Foster
    0.74
    Act Density 0.017%

    No Known Activations