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

    Neuronpedia

    INDEX
    Explanations

    references to horror movies

    oai_token-act-pair · gpt-3.5-turbo

    references to horror

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.81
    dated
    -0.81
    onga
    -0.71
    cially
    -0.70
    arity
    -0.67
    lease
    -0.66
    ients
    -0.66
    heet
    -0.66
    onso
    -0.65
    nington
    -0.64
    POSITIVE LOGITS
     Horror
    1.11
    genre
    0.88
     horror
    0.85
     flick
    0.85
    crow
    0.85
     movies
    0.84
    Alien
    0.83
     movie
    0.82
     craw
    0.81
     crawl
    0.81
    Act Density 0.050%

    No Known Activations