INDEX
    Explanations

    terms related to the film and entertainment industry

    New Auto-Interp
    Negative Logits
     tiết
    -0.15
    oldem
    -0.14
     Invent
    -0.14
     Bicycle
    -0.14
    imin
    -0.13
    .Views
    -0.13
     vacc
    -0.13
    áb
    -0.13
    731
    -0.13
    itzer
    -0.13
    POSITIVE LOGITS
     radio
    0.36
     motion
    0.34
     TV
    0.27
    radio
    0.27
    motion
    0.26
     television
    0.25
     Motion
    0.24
     stage
    0.24
     animation
    0.23
     Radio
    0.23
    Act Density 0.223%

    No Known Activations