INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bes
    -0.84
     post
    -0.84
     pre
    -0.83
     po
    -0.82
     der
    -0.82
     par
    -0.80
     pr
    -0.78
    walde
    -0.77
     ro
    -0.76
     ph
    -0.76
    POSITIVE LOGITS
     ſever
    1.39
     itſelf
    1.37
     Majefty
    1.35
     ſche
    1.34
     pleaſure
    1.33
     Monfieur
    1.33
     houſe
    1.32
     ſeveral
    1.30
     Efq
    1.30
     myſelf
    1.29
    Act Density 2.813%

    No Known Activations