INDEX
    Explanations

    abbreviations

    New Auto-Interp
    Negative Logits
    тино
    -0.49
     J
    -0.47
     w
    -0.46
     W
    -0.46
    es
    -0.45
     her
    -0.44
     di
    -0.43
     g
    -0.42
     bur
    -0.42
    behör
    -0.42
    POSITIVE LOGITS
     Efq
    1.47
     myſelf
    1.33
     Monfieur
    1.23
     Theſe
    1.18
     Majefty
    1.13
     themſelves
    1.11
     poffible
    1.11
     fubject
    1.09
     Jefus
    1.08
     Anſ
    1.08
    Act Density 0.179%

    No Known Activations