INDEX
    Explanations

    code/technical documentation

    New Auto-Interp
    Negative Logits
     C
    -0.53
     (
    -0.53
     M
    -0.53
     Mun
    -0.52
    -0.50
    -0.50
     la
    -0.50
     II
    -0.49
     z
    -0.48
     L
    -0.48
    POSITIVE LOGITS
     contextLoads
    0.94
    الحياه
    0.94
     tranſ
    0.88
     referenties
    0.86
    Geplaatst
    0.84
    PerformLayout
    0.82
     juſt
    0.82
    UnusedPrivate
    0.81
    posedge
    0.79
    ſelf
    0.79
    Act Density 1.582%

    No Known Activations