INDEX
    Explanations

    Numerical calculations

    New Auto-Interp
    Negative Logits
    ::_
    -0.08
    .od
    -0.08
     vase
    -0.07
     INR
    -0.07
    scp
    -0.07
     enf
    -0.07
    -0.07
    /sc
    -0.07
    otify
    -0.07
    unen
    -0.07
    POSITIVE LOGITS
    Contribution
    0.11
     contributions
    0.11
     contribution
    0.11
    0.09
     added
    0.09
     bijdrage
    0.09
     contributes
    0.09
     contributed
    0.08
     ઉમ
    0.08
     Contributions
    0.08
    Act Density 0.075%

    No Known Activations