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
    ANTAGE
    -0.74
     Rache
    -0.74
     trône
    -0.70
     Vrij
    -0.70
    squeeze
    -0.67
    Vrij
    -0.67
    संद
    -0.65
    zura
    -0.64
     repres
    -0.63
    =>$
    -0.63
    POSITIVE LOGITS
     films
    1.48
     FILM
    1.47
     film
    1.42
     Film
    1.39
     Films
    1.31
     FILMS
    1.28
    films
    1.26
    film
    1.26
    Films
    1.25
    Film
    1.23
    Act Density 0.066%

    No Known Activations