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

    Neuronpedia

    INDEX
    Explanations

    references to spiritual or supernatural entities, particularly demons

    oai_token-act-pair · gpt-3.5-turbo

    references to "demon" and its variations within different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.70
    RAFT
    -0.69
     Seym
    -0.69
    sburgh
    -0.68
     proble
    -0.63
    ills
    -0.62
    abouts
    -0.60
     Crosby
    -0.60
    hiba
    -0.60
    å
    -0.59
    POSITIVE LOGITS
    stration
    1.38
    iac
    1.11
    strate
    0.99
    ormal
    0.96
    ising
    0.91
    ises
    0.90
    oid
    0.87
    bolt
    0.83
    izing
    0.83
    ica
    0.83
    Act Density 0.013%

    No Known Activations