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

    Neuronpedia

    INDEX
    Explanations

    words related to demons

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Demon" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.91
    RAFT
    -0.78
    tta
    -0.75
    leneck
    -0.71
    ills
    -0.67
    entric
    -0.64
    Pg
    -0.63
    lahoma
    -0.60
    raltar
    -0.60
     Crosby
    -0.60
    POSITIVE LOGITS
    stration
    1.21
     Demon
    1.07
    demon
    1.03
    Demon
    0.93
    strate
    0.87
    ciples
    0.85
     exorc
    0.73
    geist
    0.73
    bats
    0.72
     Maiden
    0.72
    Act Density 0.007%

    No Known Activations