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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Harry"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Harry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.75
    PLA
    -0.73
    tical
    -0.69
    oute
    -0.66
    ocr
    -0.65
    ourced
    -0.65
    our
    -0.63
    asio
    -0.61
    awaru
    -0.61
    ations
    -0.60
    POSITIVE LOGITS
     Potter
    1.33
     Dresden
    0.95
     Styles
    0.93
    haus
    0.92
     Reid
    0.90
     Truman
    0.86
     Kane
    0.77
    STON
    0.76
    stones
    0.74
    XX
    0.70
    Act Density 0.028%

    No Known Activations