INDEX
    Explanations

    legal terminology related to court cases and references to specific individuals involved in legal matters

    New Auto-Interp
    Negative Logits
     Tag
    -0.73
     Tags
    -0.68
     Tome
    -0.67
     Bremen
    -0.67
    TagHelper
    -0.66
     Mun
    -0.65
     ausz
    -0.65
     Braun
    -0.63
     Schwartz
    -0.63
    -0.63
    POSITIVE LOGITS
    .)}
    0.99
    )++;
    0.90
     ){
    
    0.88
     }}$}
    0.87
    )];
    
    0.87
     Saxe
    0.86
    `,
    
    0.85
     donkeys
    0.85
    ]';
    0.84
     Erskine
    0.84
    Act Density 3.429%

    No Known Activations