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

    Neuronpedia

    INDEX
    Explanations

    text related to people's names, especially "Catherine" and "Shepard."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Catherine" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.94
    oard
    -0.83
    keye
    -0.82
    yip
    -0.78
    lass
    -0.76
    eties
    -0.75
    rities
    -0.74
    oras
    -0.74
    lux
    -0.74
    orage
    -0.74
    POSITIVE LOGITS
    ICAL
    0.69
     Weed
    0.69
    FUL
    0.67
     Reincarnated
    0.66
    Dialogue
    0.64
     Mechdragon
    0.62
    ically
    0.62
    iano
    0.60
     Benz
    0.60
    lain
    0.60
    Act Density 0.064%

    No Known Activations