INDEX
    Explanations

    punctuation marks, particularly semicolons and commas

    Punctuation, numbers, or special characters

    New Auto-Interp
    Negative Logits
    ?')
    -0.94
    %")
    -0.91
     }}$}
    -0.90
    ++
    
    -0.88
    NUMX
    -0.88
    ^(@)
    -0.86
     Efq
    -0.86
    tvguidetime
    -0.84
     setuptools
    -0.84
    !")
    
    -0.83
    POSITIVE LOGITS
     it
    0.98
     there
    0.95
    .
    0.91
     I
    0.88
     but
    0.87
     we
    0.82
    ↵↵
    0.82
     they
    0.81
     There
    0.81
     although
    0.81
    Act Density 0.398%

    No Known Activations