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

    Neuronpedia

    INDEX
    Explanations

    references to catastrophic events, particularly apocalyptic scenarios, in the text

    oai_token-act-pair · gpt-3.5-turbo

    narrative elements related to apocalyptic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEA
    -0.77
    Recomm
    -0.75
     Nguyen
    -0.74
    ellectual
    -0.71
    emade
    -0.70
    ª
    -0.68
    Lean
    -0.68
    ients
    -0.68
    ulton
    -0.67
    ket
    -0.67
    POSITIVE LOGITS
    bringer
    1.04
     doom
    0.92
     Predator
    0.89
     Incarn
    0.89
     prophes
    0.88
    ocalypse
    0.87
     Doomsday
    0.87
     reckoning
    0.86
    hower
    0.85
     havoc
    0.85
    Act Density 0.096%

    No Known Activations