INDEX
    Explanations

    references to political commentary or discussions

    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.60
    Personensuche
    -0.52
    AccessorTable
    -0.51
    Rohy
    -0.50
    ьаж
    -0.47
    StructEnd
    -0.46
    Портали
    -0.45
    archiwizowane
    -0.44
    RTLD
    -0.44
    Aholisi
    -0.43
    POSITIVE LOGITS
     blogging
    0.55
     tweeted
    0.53
     blog
    0.53
    Blog
    0.52
     Blog
    0.51
     tweeting
    0.51
     Blogging
    0.49
    rungsseite
    0.48
    それにしても
    0.48
     twit
    0.48
    Act Density 0.766%

    No Known Activations