INDEX
    Explanations

    numeric and date-related information in the text

    New Auto-Interp
    Negative Logits
    uji
    -0.16
    u
    -0.15
     ind
    -0.14
    lag
    -0.14
    an
    -0.14
    ued
    -0.14
    urtles
    -0.14
    ISK
    -0.14
    UED
    -0.14
    :
    -0.13
    POSITIVE LOGITS
    оÑģÑĤав
    0.17
    å¦ĸ
    0.17
     nackte
    0.16
    uthor
    0.15
    æľŃ
    0.15
    лика
    0.15
    ä½ľèĢħ
    0.15
    æŁ»
    0.14
    ony
    0.14
    Ä©
    0.14
    Act Density 0.005%

    No Known Activations