INDEX
    Explanations

    references to specific geographic locations and their features

    New Auto-Interp
    Negative Logits
     quadr
    -0.14
    ideo
    -0.14
    Ã¤ÃŁ
    -0.14
     fil
    -0.14
    zin
    -0.14
    NECT
    -0.14
    urity
    -0.14
    λει
    -0.14
    elman
    -0.13
    nex
    -0.13
    POSITIVE LOGITS
     Couples
    0.16
    untu
    0.16
     Comb
    0.14
    -ı
    0.14
    hots
    0.14
    abela
    0.14
    že
    0.14
    kan
    0.14
    å©ļ
    0.14
    ulpt
    0.13
    Act Density 0.188%

    No Known Activations