INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .
    -0.81
     (
    -0.76
     a
    -0.75
     in
    -0.73
     to
    -0.73
     for
    -0.72
     so
    -0.72
     as
    -0.71
    -0.69
     an
    -0.68
    POSITIVE LOGITS
     Efq
    2.33
     Theſe
    2.31
     Monfieur
    2.28
     myſelf
    2.27
     Jefus
    2.14
     Anſ
    2.11
     itſelf
    2.09
     Majefty
    2.05
     Houſe
    2.02
     Reſ
    1.98
    Act Density 1.273%

    No Known Activations