INDEX
    Explanations

    names of people associated with the film industry

    New Auto-Interp
    Negative Logits
    ẫ
    -0.16
    /WebAPI
    -0.14
     prefix
    -0.14
    ylon
    -0.14
     resid
    -0.14
    braco
    -0.14
    ennen
    -0.13
    ewis
    -0.13
    DonaldTrump
    -0.13
    æk
    -0.13
    POSITIVE LOGITS
    315
    0.16
    aos
    0.15
    ergus
    0.14
     Additional
    0.14
    173
    0.14
     Mor
    0.14
    579
    0.14
     Freeze
    0.13
    oom
    0.13
     rally
    0.13
    Act Density 0.019%

    No Known Activations