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

    Neuronpedia

    INDEX
    Explanations

    mentions of characters and their roles in a story or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Katharine
    -0.61
     Gwend
    -0.61
     Mahabhar
    -0.59
     Aleksander
    -0.57
     alexander
    -0.57
     Aleksandra
    -0.57
     ALEXANDER
    -0.57
    Nicholas
    -0.57
     supérieures
    -0.57
    льников
    -0.57
    POSITIVE LOGITS
     Bob
    0.82
     Pete
    0.79
    uzzy
    0.77
     Mike
    0.76
     Dave
    0.76
     Bill
    0.73
     Doc
    0.71
     Joe
    0.71
     Tony
    0.70
     Eddie
    0.70
    Act Density 0.160%

    No Known Activations