INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    eload
    -0.08
    Barr
    -0.08
     зон
    -0.08
     Barr
    -0.08
    -0.07
    riere
    -0.07
     apost
    -0.07
     nemlig
    -0.07
    ístup
    -0.07
    ань
    -0.07
    POSITIVE LOGITS
     able
    0.09
    如此
    0.09
     ktoś
    0.09
     foreigners
    0.08
     CRT
    0.08
     mortality
    0.07
     regression
    0.07
     atol
    0.07
     ability
    0.07
     LA
    0.07
    Act Density 0.049%

    No Known Activations