INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    uttavia
    -0.56
     professeur
    -0.55
     vôtre
    -0.52
    Mathias
    -0.51
     us
    -0.49
    luit
    -0.48
     symboles
    -0.48
     مشين
    -0.47
     bulat
    -0.47
     ơn
    -0.47
    POSITIVE LOGITS
    ſelf
    0.82
     GenerationType
    0.78
     pleaſure
    0.68
    PerformLayout
    0.67
    CppCodeGen
    0.61
    })*/
    0.61
    ſelves
    0.59
     Majefty
    0.59
    featureID
    0.58
    ValueStyle
    0.58
    Act Density 0.003%

    No Known Activations