INDEX
    Explanations

    references to political leadership and government officials

    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.48
    WaitGroup
    -0.37
    vikle
    -0.35
    IsContent
    -0.35
    indicato
    -0.35
     kru
    -0.34
    AndFlush
    -0.34
    yarnpkg
    -0.34
     excru
    -0.34
     complexity
    -0.34
    POSITIVE LOGITS
     Meets
    0.49
    fjspx
    0.48
    RTGC
    0.45
     designate
    0.45
    SBATCH
    0.44
    duled
    0.43
     sacked
    0.41
     Visits
    0.41
    }{{
    0.40
     accett
    0.40
    Act Density 0.377%

    No Known Activations