INDEX
    Explanations

    references to the current date or usage of the word "today."

    New Auto-Interp
    Negative Logits
    leaf
    -0.18
     Laur
    -0.16
    ussen
    -0.16
    ÙĦاÙģ
    -0.16
     now
    -0.15
    ray
    -0.15
    er
    -0.15
    ely
    -0.15
    bet
    -0.15
    su
    -0.15
    POSITIVE LOGITS
    lerde
    0.23
    aday
    0.19
    eÄį
    0.16
    jÅ¡ÃŃ
    0.16
    arro
    0.15
    ÑĪ
    0.15
    Ùħار
    0.15
    گار
    0.15
    -day
    0.15
     createState
    0.15
    Act Density 0.043%

    No Known Activations