INDEX
    Explanations

    mentions of online forums or forum-related content

    New Auto-Interp
    Negative Logits
     mas
    -0.28
    a
    -0.27
    an
    -0.27
     է
    -0.26
       
    -0.25
    cli
    -0.25
    al
    -0.24
     везде
    -0.23
    antd
    -0.23
    ></
    -0.23
    POSITIVE LOGITS
    forum
    2.45
    Forum
    2.25
     Forum
    2.03
    FORUM
    1.87
     FORUM
    1.73
    forums
    1.56
    Forums
    1.54
     forum
    1.54
     Forums
    1.41
     forums
    1.13
    Act Density 0.003%

    No Known Activations