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

    Neuronpedia

    INDEX
    Explanations

    references to the "Harry Potter" series

    oai_token-act-pair · gpt-3.5-turbo

    references to the Harry Potter series and its characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resp
    -0.77
    ©¶æ
    -0.74
    oples
    -0.71
    ¡
    -0.67
     ASA
    -0.65
    ioxide
    -0.64
     contrad
    -0.63
     incent
    -0.63
    IGN
    -0.63
    PsyNetMessage
    -0.62
    POSITIVE LOGITS
     Potter
    1.02
     Granger
    0.90
    more
    0.87
     Weasley
    0.87
     Dumbledore
    0.86
    haus
    0.86
    wra
    0.82
     Hogwarts
    0.81
     Rowling
    0.80
    uggle
    0.79
    Act Density 0.046%

    No Known Activations