INDEX
    Explanations

    animate or aboriginal topics

    New Auto-Interp
    Negative Logits
     myſelf
    -1.16
     themſelves
    -1.05
     Efq
    -1.05
     itſelf
    -1.05
     whoſe
    -1.04
     Reſ
    -1.03
     purpoſe
    -1.02
     Theſe
    -1.02
     Monfieur
    -1.02
     Chriftian
    -1.01
    POSITIVE LOGITS
    <bos>
    0.59
    0.55
    </strong>
    0.52
     S
    0.49
     A
    0.48
     Te
    0.48
    м
    0.48
     E
    0.47
     O
    0.47
     "
    0.47
    Act Density 0.094%

    No Known Activations