INDEX
    Explanations

    references to a serious or bleak tone in the text

    New Auto-Interp
    Negative Logits
     Brunswick
    -0.16
    .scalablytyped
    -0.15
    itra
    -0.15
     pic
    -0.15
    ielding
    -0.14
     çľģ
    -0.14
    astes
    -0.14
    swick
    -0.14
    676
    -0.14
     rak
    -0.14
    POSITIVE LOGITS
    bot
    0.16
    balls
    0.15
     Bot
    0.15
    -bot
    0.14
    nop
    0.14
    mong
    0.14
    ly
    0.14
    uid
    0.14
    bon
    0.14
    mond
    0.14
    Act Density 0.011%

    No Known Activations