INDEX
    Explanations

    expressions highlighting significance or importance

    New Auto-Interp
    Negative Logits
    resizingMask
    -0.66
    xhtml
    -0.65
     metropolitana
    -0.65
    ed
    -0.64
    зец
    -0.63
    er
    -0.62
    ers
    -0.61
    oflavin
    -0.61
    after
    -0.57
     profeta
    -0.57
    POSITIVE LOGITS
     Important
    1.59
     important
    1.51
    Important
    1.50
    important
    1.43
     importance
    1.38
     Importance
    1.35
    Importance
    1.32
    importance
    1.30
    IMPORTANT
    1.29
     IMPORTANT
    1.28
    Act Density 0.061%

    No Known Activations