INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kamer
    -0.08
     aneur
    -0.08
    Slim
    -0.08
    Bulk
    -0.08
     bulk
    -0.07
     lar
    -0.07
     radio
    -0.07
    Pak
    -0.07
     nanop
    -0.07
     packaged
    -0.07
    POSITIVE LOGITS
     duke
    0.09
    0.09
    hebb
    0.09
    认可
    0.09
     Allowed
    0.08
     recommandé
    0.08
     három
    0.08
     Constitucional
    0.08
     మూడు
    0.08
     Cardinal
    0.08
    Act Density 0.005%

    No Known Activations