INDEX
    Explanations

    HTML tags and structure in the document

    New Auto-Interp
    Negative Logits
    zeit
    -0.18
     CRT
    -0.15
    jit
    -0.15
    ivant
    -0.15
    ITCH
    -0.15
     Diana
    -0.14
     jung
    -0.14
     Undert
    -0.14
    ixe
    -0.14
    using
    -0.14
    POSITIVE LOGITS
    td
    0.59
     td
    0.50
    <td
    0.47
    TD
    0.47
    (td
    0.45
    	td
    0.43
    _td
    0.43
     TD
    0.40
    Td
    0.38
    _TD
    0.33
    Act Density 0.018%

    No Known Activations