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

    Neuronpedia

    INDEX
    Explanations

    references to horror-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to horror as a genre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.76
    ional
    -0.72
    cially
    -0.69
    ioned
    -0.66
    ients
    -0.65
    equality
    -0.64
    onso
    -0.64
     Brune
    -0.63
    change
    -0.62
    arity
    -0.62
    POSITIVE LOGITS
    crow
    1.18
     craw
    1.02
     Horror
    0.95
    mong
    0.87
     crawl
    0.84
     clown
    0.84
     Masquerade
    0.82
     haunted
    0.80
     Nights
    0.80
     movie
    0.78
    Act Density 0.117%

    No Known Activations