INDEX
    Explanations

    statements related to political campaigns and candidate claims

    Political and partisan content

    political propaganda and fake news

    New Auto-Interp
    Negative Logits
     dreamer
    -0.48
     bondage
    -0.48
     Graphite
    -0.47
     lockers
    -0.46
    UrlResolution
    -0.46
    Collect
    -0.46
     sogno
    -0.44
    abuhan
    -0.43
    ouac
    -0.42
    RectangleBorder
    -0.42
    POSITIVE LOGITS
     political
    0.90
    tifact
    0.85
    political
    0.77
     Political
    0.76
     partisan
    0.73
    Political
    0.70
     platforms
    0.66
     electoral
    0.65
     election
    0.63
     counter
    0.63
    Act Density 0.362%

    No Known Activations