INDEX
    Explanations

    mentions of social media platforms, particularly Twitter

    New Auto-Interp
    Negative Logits
    igham
    -0.15
     Us
    -0.14
     ay
    -0.14
     responsible
    -0.14
    akat
    -0.14
     代
    -0.14
    ddl
    -0.14
    otts
    -0.14
    owie
    -0.14
     Webster
    -0.13
    POSITIVE LOGITS
    .com
    0.20
    iou
    0.16
    pic
    0.16
     pic
    0.16
    ÑĢеб
    0.16
    THREAD
    0.16
    ultipartFile
    0.15
    Envelope
    0.15
    .COM
    0.14
    _https
    0.13
    Act Density 0.002%

    No Known Activations