INDEX
    Explanations

    punctuation marks and special characters in the text

    New Auto-Interp
    Negative Logits
    ãģ¾ãģ¾
    -0.15
    iros
    -0.15
    arma
    -0.15
     flip
    -0.14
     rebellion
    -0.14
     Dude
    -0.14
     Flip
    -0.14
     smr
    -0.14
    412
    -0.14
    anim
    -0.14
    POSITIVE LOGITS
    ijk
    0.14
    Insets
    0.14
    (tol
    0.14
    ahlen
    0.14
    è¾°
    0.14
    adders
    0.14
    /forms
    0.14
    .ht
    0.13
    é̲
    0.13
    ç´«
    0.13
    Act Density 0.000%

    No Known Activations