INDEX
    Explanations

    mentions of social media platforms

    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.63
    DockStyle
    -0.57
    qtype
    -0.54
    providedIn
    -0.47
    ThroughAttribute
    -0.46
    KommentareTeilen
    -0.45
    RotationOrder
    -0.45
    olerance
    -0.44
     ModelExpression
    -0.43
    rrggbb
    -0.41
    POSITIVE LOGITS
     Facebook
    0.89
     Twitter
    0.82
     Instagram
    0.81
    Instagram
    0.79
    Facebook
    0.78
    Twitter
    0.76
     facebook
    0.75
     TWITTER
    0.74
     FACEBOOK
    0.73
     twitter
    0.73
    Act Density 0.163%

    No Known Activations