INDEX
    Explanations

    references to films and cinematic elements

    New Auto-Interp
    Negative Logits
    erial
    -0.17
    sher
    -0.15
    .appspot
    -0.14
    SSF
    -0.14
    uve
    -0.14
    inos
    -0.14
     Dod
    -0.14
    atro
    -0.14
    .hasMore
    -0.14
    uteur
    -0.13
    POSITIVE LOGITS
    quia
    0.16
    ogle
    0.15
    movie
    0.15
    /movie
    0.14
    Verb
    0.14
    olec
    0.13
    -inspired
    0.13
    bib
    0.13
    /book
    0.13
     DataRow
    0.13
    Act Density 0.241%

    No Known Activations