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

    Neuronpedia

    INDEX
    Explanations

    references to vampire characters

    oai_token-act-pair · gpt-3.5-turbo

    references to vampires and vampire-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OS
    -0.87
    Jam
    -0.85
     Iw
    -0.83
    IJ
    -0.82
     Manning
    -0.78
     Kerr
    -0.77
     AFC
    -0.77
     Howe
    -0.76
     Lewis
    -0.76
     OU
    -0.76
    POSITIVE LOGITS
     vampire
    3.28
     vampires
    3.23
     Vampire
    3.12
    ampire
    2.42
     Dracula
    2.36
    ampires
    2.02
     Werewolf
    1.87
     Buffy
    1.70
    wolves
    1.43
     Cullen
    1.39
    Act Density 0.046%

    No Known Activations