INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     fractional
    -0.07
     Dice
    -0.07
     occasionally
    -0.07
    زمان
    -0.06
     lat
    -0.06
     tz
    -0.06
     Kraj
    -0.06
    unday
    -0.06
     scraped
    -0.06
     ladder
    -0.06
    POSITIVE LOGITS
     Support
    0.13
     support
    0.13
    .support
    0.10
    support
    0.09
    0.09
    Support
    0.09
     SUPPORT
    0.09
     supports
    0.09
     supporting
    0.09
    -support
    0.08
    Act Density 0.051%

    No Known Activations