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

    Neuronpedia

    INDEX
    Explanations

    references to movies and movie-related contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     meis
    -1.22
     aen
    -1.19
     ivi
    -1.18
     „,
    -1.17
     unan
    -1.17
     lele
    -1.15
     dises
    -1.15
     pessi
    -1.14
     secon
    -1.13
     Juf
    -1.13
    POSITIVE LOGITS
    才能
    0.93
     before
    0.80
     to
    0.80
     כדי
    0.78
     чтобы
    0.78
     để
    0.74
     because
    0.72
    来
    0.71
     unless
    0.70
     must
    0.69
    Act Density 0.498%

    No Known Activations