INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    yes
    -1.02
    YES
    -0.79
    yet
    -0.75
    ye
    -0.73
    ying
    -0.65
    yay
    -0.65
     yes
    -0.59
    yi
    -0.57
    yin
    -0.56
    yo
    -0.56
    POSITIVE LOGITS
    InjectAttribute
    0.80
     للمعارف
    0.80
    apimachinery
    0.72
    IUrlHelper
    0.71
     Monfieur
    0.69
    WithMany
    0.68
    CompilerServices
    0.68
     vPvB
    0.68
     nemico
    0.67
     réelle
    0.66
    Act Density 0.067%

    No Known Activations