INDEX
    Explanations

    references to messaging applications and their characteristics

    New Auto-Interp
    Negative Logits
    umpt
    -0.14
    pons
    -0.14
    oled
    -0.14
    ole
    -0.14
    svp
    -0.14
    ieee
    -0.13
    _cf
    -0.13
    pled
    -0.13
    resa
    -0.13
    Ķ
    -0.13
    POSITIVE LOGITS
     chat
    0.62
     Chat
    0.55
    chat
    0.54
    -chat
    0.52
    Chat
    0.51
     chats
    0.50
     chatting
    0.48
    _chat
    0.46
    èģĬ
    0.45
    .chat
    0.43
    Act Density 0.158%

    No Known Activations