INDEX
    Explanations

    characteristics related to formatting or typesetting in documents

    Characters surrounding superscripts

    New Auto-Interp
    Negative Logits
    expandindo
    -1.29
    .)}
    -1.00
    .")]
    -0.97
    '],
    
    -0.96
    .")
    
    -0.94
    ).}
    -0.93
    ]$}
    -0.92
    ).</
    -0.89
    ')],
    -0.88
    "):
    
    -0.88
    POSITIVE LOGITS
    0.65
     ,
    0.64
    j
    0.63
    «
    0.59
     .
    0.57
    »
    0.55
    J
    0.55
    .,
    0.54
    ^
    0.54
     „
    0.53
    Act Density 0.100%

    No Known Activations