INDEX
    Explanations

    Technical/scientific topics

    New Auto-Interp
    Negative Logits
     greateſt
    -0.93
     auffi
    -0.78
     myſelf
    -0.77
     itſelf
    -0.75
     Monfieur
    -0.74
     ainfi
    -0.73
     beſt
    -0.70
     intentionally
    -0.69
     whoſe
    -0.69
     themſelves
    -0.69
    POSITIVE LOGITS
    providedIn
    0.64
    y
    0.59
     et
    0.54
    InjectAttribute
    0.50
     es
    0.50
     Wall
    0.50
     Person
    0.50
     v
    0.49
     dane
    0.48
    niająca
    0.48
    Act Density 0.635%

    No Known Activations