INDEX
    Explanations

    references to time, particularly periods of days, years, and points in time

    New Auto-Interp
    Negative Logits
    499
    -0.15
    iam
    -0.14
    orks
    -0.14
    intColor
    -0.13
    133
    -0.13
    jev
    -0.13
    ata
    -0.13
    abei
    -0.13
    ’d
    -0.13
    ana
    -0.12
    POSITIVE LOGITS
     there
    0.17
    ,
    0.17
     ÙħÛĮÙĦادÛĮ
    0.14
     thì
    0.14
    Mahon
    0.14
    -toggler
    0.14
     RVA
    0.13
     we
    0.13
    fort
    0.13
    ceptor
    0.13
    Act Density 0.186%

    No Known Activations