INDEX
    Explanations

    punctuation marks, specifically periods

    New Auto-Interp
    Negative Logits
    ibbon
    -0.17
    noinspection
    -0.16
    raith
    -0.15
    tmpl
    -0.14
    à¥ĭध
    -0.14
    688
    -0.14
    azz
    -0.13
    isay
    -0.13
    hythm
    -0.13
    iba
    -0.13
    POSITIVE LOGITS
     ضÙħÙĨ
    0.16
    uses
    0.14
    ź
    0.14
    .wind
    0.14
     Tou
    0.14
    otec
    0.14
     ragaz
    0.14
    unde
    0.14
    Ds
    0.14
    tons
    0.14
    Act Density 0.001%

    No Known Activations