INDEX
    Explanations

    references to the concept of time, particularly durations of hours

    New Auto-Interp
    Negative Logits
    anned
    -0.14
    ica
    -0.14
    باÙĨ
    -0.14
     ay
    -0.14
    ard
    -0.14
    Ñıг
    -0.14
    shal
    -0.13
     shade
    -0.13
    ym
    -0.13
    oyo
    -0.13
    POSITIVE LOGITS
    idon
    0.16
    omens
    0.15
    -long
    0.15
    poons
    0.15
    Úĺ
    0.14
    erli
    0.14
    alah
    0.14
    emarks
    0.14
    _nan
    0.14
     Tes
    0.14
    Act Density 0.026%

    No Known Activations