INDEX
    Explanations

    terms related to film and award nominations

    New Auto-Interp
    Negative Logits
    okino
    -0.15
    åŁº
    -0.14
     Sink
    -0.14
    ÅĻel
    -0.14
    iens
    -0.14
    Ģ
    -0.14
     bis
    -0.13
    Sink
    -0.13
    ooter
    -0.13
    .utf
    -0.13
    POSITIVE LOGITS
    _common
    0.15
    å¥ī
    0.14
    ilo
    0.14
    Ñľ
    0.14
    at
    0.14
    paper
    0.14
    عÙĨ
    0.14
    ÙĤب
    0.14
    qv
    0.14
    lub
    0.14
    Act Density 0.019%

    No Known Activations