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

    Neuronpedia

    INDEX
    Explanations

    the name "Walter"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Walter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arian
    -0.91
    ional
    -0.91
    ebook
    -0.90
    arians
    -0.89
    expr
    -0.84
    onal
    -0.79
    unity
    -0.78
    oral
    -0.77
    ocre
    -0.77
    atories
    -0.76
    POSITIVE LOGITS
     Mond
    1.14
     Reed
    0.93
     Winc
    0.88
     Sob
    0.86
     Payton
    0.81
    ston
    0.81
     Cron
    0.81
     Isaac
    0.81
     Ley
    0.78
     Walter
    0.76
    Act Density 0.031%

    No Known Activations