INDEX
    Explanations

    ordinal numbers and their representations in the text

    New Auto-Interp
    Negative Logits
    ierz
    -0.17
    ythe
    -0.16
    eras
    -0.15
     rej
    -0.14
    pars
    -0.14
     YEARS
    -0.14
    hip
    -0.14
    жен
    -0.14
    urus
    -0.14
    еÑģÑĤÑĮ
    -0.14
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.17
    chen
    0.15
    elts
    0.15
    ekli
    0.14
    ilde
    0.14
    loe
    0.14
    elsius
    0.14
    ially
    0.13
    agen
    0.13
    UTC
    0.13
    Act Density 0.014%

    No Known Activations