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

    Neuronpedia

    INDEX
    Explanations

    references to the horror genre

    oai_token-act-pair · gpt-3.5-turbo

    references to the horror genre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dated
    -0.95
    cially
    -0.80
    inion
    -0.71
    eded
    -0.68
    pai
    -0.67
    manent
    -0.66
    pleting
    -0.66
    artney
    -0.64
    FW
    -0.64
    legates
    -0.64
    POSITIVE LOGITS
     Horror
    1.20
     horror
    1.09
     Cthulhu
    0.83
    mong
    0.79
    crow
    0.78
     Outbreak
    0.77
     plag
    0.76
     Scythe
    0.74
     horrors
    0.74
     Panic
    0.74
    Act Density 0.013%

    No Known Activations