INDEX
    Explanations

    references to political figures and their roles in government

    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.54
    contentLoaded
    -0.53
    __()
    -0.48
    #
    -0.46
     >=",
    -0.44
    Etymology
    -0.44
    _<
    -0.43
    Ikus
    -0.43
     mediu
    -0.43
     Compro
    -0.43
    POSITIVE LOGITS
     المعيارى
    0.66
    DockStyle
    0.63
     Roskov
    0.61
    قایناق‌لار
    0.57
    design
    0.56
     tweeted
    0.56
    twimg
    0.56
     designate
    0.55
    igshid
    0.54
     HE
    0.54
    Act Density 0.202%

    No Known Activations