INDEX
    Explanations

    Programming code

    New Auto-Interp
    Negative Logits
     "
    -0.81
     “
    -0.77
    ,
    -0.71
     I
    -0.68
     or
    -0.67
    -0.66
     in
    -0.64
     M
    -0.64
     V
    -0.64
    i
    -0.63
    POSITIVE LOGITS
     myſelf
    1.90
     Efq
    1.78
     itſelf
    1.76
     raiſ
    1.72
     Monfieur
    1.69
     themſelves
    1.66
     Majefty
    1.65
     Jefus
    1.63
     purpoſe
    1.63
     himſelf
    1.62
    Act Density 0.056%

    No Known Activations