INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     months
    0.64
    Months
    0.63
     Months
    0.61
    months
    0.55
     indefinitely
    0.54
     meses
    0.54
     maanden
    0.53
     weeks
    0.52
    一段时间
    0.48
     Monaten
    0.48
    POSITIVE LOGITS
    (!)
    0.52
     praticamente
    0.51
     witnessing
    0.50
     (!)
    0.50
     worth
    0.49
     untold
    0.48
     watching
    0.46
     거의
    0.46
     honing
    0.46
     wars
    0.45
    Act Density 0.013%

    No Known Activations