INDEX
    Explanations

    occurrences of HTML script tags in the document

    New Auto-Interp
    Negative Logits
    ese
    -0.17
    ils
    -0.16
    ust
    -0.15
    essa
    -0.14
    о
    -0.14
    aster
    -0.14
    ษ
    -0.14
    /inet
    -0.14
    obile
    -0.14
    ach
    -0.14
    POSITIVE LOGITS
    æ¸
    0.17
    -addon
    0.15
    ī
    0.15
    ylene
    0.15
    inalg
    0.15
     Nová
    0.14
    ëĤľ
    0.14
    ãĥ³ãĤº
    0.14
    à¹īำหà¸Ļ
    0.14
    auen
    0.14
    Act Density 0.001%

    No Known Activations