INDEX
    Explanations

    legal and scientific terminologies related to case law and environmental impact

    Punctuated tokens, especially dashes

    dashes or explanatory punctuation

    New Auto-Interp
    Negative Logits
    \{\\
    -1.20
    ."));
    -1.13
    .");
    
    -1.11
    ".
    
    -1.10
    .")
    
    -1.09
    .";
    
    -1.07
    '))
    
    -1.06
    .",
    
    -1.03
    ?");
    -1.03
    )");
    
    -1.01
    POSITIVE LOGITS
     –
    2.18
     —
    2.17
     -
    2.15
     --
    2.01
    1.89
    --
    1.60
     −
    1.54
     –,
    1.53
     -,
    1.45
    1.43
    Act Density 0.331%

    No Known Activations