INDEX
    Explanations

    mentions of the social media platform Twitter

    New Auto-Interp
    Negative Logits
     izvē
    -0.70
    Ainda
    -0.62
     vairāk
    -0.60
     يتيمه
    -0.59
    ỡng
    -0.57
    <?
    -0.56
    DebuggerStep
    -0.56
    IActionResult
    -0.56
    BindingResult
    -0.56
    EndInit
    -0.55
    POSITIVE LOGITS
     Twitter
    1.27
     twitter
    1.27
    Twitter
    1.18
    twitter
    1.12
     tweeting
    1.09
     tweets
    1.07
     Tweets
    1.03
     twit
    1.02
     tweet
    1.00
     TWITTER
    0.95
    Act Density 0.037%

    No Known Activations