INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ſelf
    -1.18
    ſelves
    -1.01
     Majefty
    -0.98
     myſelf
    -0.98
     raiſ
    -0.98
     iſt
    -0.97
     purpoſe
    -0.96
     bezeichneter
    -0.93
     pleaſure
    -0.93
     Jefus
    -0.92
    POSITIVE LOGITS
    !
    0.55
     to
    0.55
    ,
    0.54
    .
    0.54
    :
    0.48
     up
    0.47
    A
    0.46
     of
    0.46
     (
    0.46
     Mérimée
    0.46
    Act Density 0.762%

    No Known Activations