INDEX
    Explanations

    punctuation marks at the end of sentences

    New Auto-Interp
    Negative Logits
    i
    -0.66
     "
    -0.63
     Carolina
    -0.60
    Zacks
    -0.59
    unmodifiable
    -0.58
    umenical
    -0.56
    rog
    -0.55
     kh
    -0.55
     For
    -0.55
     Cunningham
    -0.55
    POSITIVE LOGITS
    AndEndTag
    1.09
    $.
    
    1.07
    '},
    
    1.04
    __":
    
    1.03
     ***!
    1.03
    )");
    
    1.01
     myſelf
    0.98
     Audiodateien
    0.97
    .";
    
    0.97
    '>";
    0.97
    Act Density 0.195%

    No Known Activations