INDEX
    Explanations

    punctuation marks at the end of sentences

    New Auto-Interp
    Negative Logits
    i
    -0.71
    umenical
    -0.61
    I
    -0.59
     mắn
    -0.59
    -0.58
    Zacks
    -0.57
    The
    -0.55
    TAG
    -0.55
    bisk
    -0.54
     Tisch
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    1.11
    )");
    
    1.11
    $.
    
    1.08
    __":
    
    1.06
    '},
    
    1.02
     שוליים
    1.01
    extAlignment
    1.01
    AndEndTag
    1.00
    >");
    
    1.00
    PerformLayout
    0.99
    Act Density 0.107%

    No Known Activations