INDEX
    Explanations

    the presence of the word "et."

    New Auto-Interp
    Negative Logits
     purpoſe
    -0.77
     deſt
    -0.72
     pleaſure
    -0.71
     perfons
    -0.69
     raiſ
    -0.69
     caufe
    -0.69
     cauſe
    -0.68
     Diſ
    -0.68
    WithIOException
    -0.68
     Eſ
    -0.66
    POSITIVE LOGITS
     al
    1.56
    al
    0.87
     Al
    0.81
     AL
    0.61
     alia
    0.60
     et
    0.57
    Al
    0.55
     el
    0.53
     ai
    0.52
    AL
    0.52
    Act Density 0.090%

    No Known Activations