INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Αθήνα
    -0.06
     prisons
    -0.06
     Labels
    -0.06
    $path
    -0.06
    Detect
    -0.06
    nginx
    -0.06
     Elections
    -0.06
    abelle
    -0.06
    _POINTS
    -0.06
    ags
    -0.06
    POSITIVE LOGITS
     survivors
    0.15
     survivor
    0.14
     Survivor
    0.09
    ivors
    0.09
     λίγ
    0.08
     senior
    0.07
    uid
    0.07
    				     
    0.07
    ันต
    0.07
    ーデ
    0.07
    Act Density 0.004%

    No Known Activations