INDEX
    Explanations

    indicators of legal or judicial processes

    Follows punctuation or special characters

    New Auto-Interp
    Negative Logits
    }
    -0.49
     <>",
    -0.45
    )
    -0.43
        
    -0.41
    ),
    -0.41
    }',
    -0.41
    }/
    -0.40
    "}"
    -0.39
    }},
    -0.38
    },
    -0.37
    POSITIVE LOGITS
    StoreMessageInfo
    0.86
    rungsseite
    0.85
    featureID
    0.84
    ſelf
    0.73
     Efq
    0.73
     juſt
    0.72
     Theſe
    0.72
     uſed
    0.71
    SourceChecksum
    0.70
     avoient
    0.69
    Act Density 0.023%

    No Known Activations