INDEX
    Explanations

    references to political actions and sanctions involving Russia, particularly related to Putin and NATO

    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.49
    Charged
    -0.43
     illuminating
    -0.42
    MemoryWarning
    -0.42
     vac
    -0.41
     CreateTagHelper
    -0.41
    TargetException
    -0.41
     eye
    -0.41
    bitat
    -0.41
    digheden
    -0.40
    POSITIVE LOGITS
     Putin
    0.59
    Putin
    0.54
     Kremlin
    0.53
     Russia
    0.50
     Russians
    0.50
     RUSS
    0.49
     Russian
    0.48
     Russland
    0.47
    Russian
    0.47
    Russia
    0.46
    Act Density 0.153%

    No Known Activations