INDEX
    Explanations

    mentions of URLs or links to online discussions and forums

    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.56
     فريبيس
    -0.51
     Monfieur
    -0.50
    aimeJ
    -0.48
     transfieras
    -0.48
     myſelf
    -0.47
    visející
    -0.45
    AddTagHelper
    -0.44
    Dichloropropane
    -0.44
     Niños
    -0.43
    POSITIVE LOGITS
     Forum
    1.12
     forum
    1.09
     forums
    0.97
    Forum
    0.94
     FORUM
    0.93
     Forums
    0.84
    órum
    0.79
    forum
    0.76
    FORUM
    0.74
    Forums
    0.73
    Act Density 0.006%

    No Known Activations