INDEX
    Explanations

    mentions and references to a specific individual on Twitter

    mentions of Donald Trump, particularly his Twitter handle

    New Auto-Interp
    Negative Logits
     captcha
    -0.75
    phis
    -0.70
     Malays
    -0.69
    Joined
    -0.65
    fig
    -0.62
     Okin
    -0.61
     Scand
    -0.61
     Brill
    -0.58
     Kus
    -0.57
    tein
    -0.57
    POSITIVE LOGITS
    realDonaldTrump
    0.80
    Jr
    0.77
    TRUMP
    0.70
    DonaldTrump
    0.68
     surrogate
    0.64
     candidacy
    0.64
     appoint
    0.63
    Tonight
    0.62
    perty
    0.60
    )
    0.59
    Act Density 0.025%

    No Known Activations