INDEX
    Explanations

    expressions of expectation and cooperation in political and social contexts

    New Auto-Interp
    Negative Logits
    俺
    -0.18
     our
    -0.16
    eln
    -0.15
    -index
    -0.15
    elp
    -0.14
    _DECL
    -0.14
     my
    -0.14
    ă
    -0.14
    ↵↵
    -0.13
    erved
    -0.13
    POSITIVE LOGITS
     Muham
    0.16
    rome
    0.15
    527
    0.14
    %D
    0.14
    онÑĮ
    0.14
    ãĥªãĤ¢
    0.13
     Whip
    0.13
    ählen
    0.13
    cih
    0.13
    à¥Ģà¤Ł
    0.13
    Act Density 0.001%

    No Known Activations