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

    Neuronpedia

    INDEX
    Explanations

    adjectives related 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
    cially
    -0.76
    iris
    -0.73
    dated
    -0.73
    hement
    -0.72
    lease
    -0.70
    ickr
    -0.70
    artney
    -0.69
    ients
    -0.69
    nington
    -0.67
    inion
    -0.67
    POSITIVE LOGITS
     Horror
    1.24
     horror
    1.03
    Alien
    0.80
     Cthulhu
    0.80
    Batman
    0.78
     flick
    0.77
     crawl
    0.76
     movie
    0.75
     tale
    0.74
    crow
    0.74
    Act Density 0.032%

    No Known Activations