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

    Neuronpedia

    INDEX
    Explanations

    references to films and filmmaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trône
    -0.71
     Vrij
    -0.70
     Rache
    -0.70
    Vrij
    -0.68
     étrang
    -0.68
    ANTAGE
    -0.66
    squeeze
    -0.66
     Anato
    -0.65
     compréhen
    -0.64
     sintético
    -0.63
    POSITIVE LOGITS
     films
    1.35
     FILM
    1.26
     film
    1.24
     Film
    1.21
     Films
    1.14
     FILMS
    1.12
    Films
    1.09
    FILM
    1.07
    film
    1.07
    films
    1.05
    Act Density 0.053%

    No Known Activations