INDEX
    Explanations

    references to films and their production

    New Auto-Interp
    Negative Logits
    een
    -0.16
    lage
    -0.16
    avic
    -0.15
    íĴĪ
    -0.15
    าà¸ģ
    -0.15
    heim
    -0.15
    ÑįÑĦ
    -0.14
    ients
    -0.14
    selling
    -0.14
    htub
    -0.14
    POSITIVE LOGITS
    strip
    0.25
     noir
    0.23
    /video
    0.19
    /software
    0.19
    fare
    0.18
    stri
    0.17
    tran
    0.17
    ic
    0.17
    go
    0.17
    590
    0.17
    Act Density 0.041%

    No Known Activations