INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     zonne
    -0.40
     Cardinale
    -0.37
     Luar
    -0.37
     Wisata
    -0.34
     \
    -0.34
     Leder
    -0.33
     hänen
    -0.32
     joka
    -0.32
     bất
    -0.32
    ↵↵
    -0.32
    POSITIVE LOGITS
    Enough
    1.41
     Enough
    1.41
    enough
    1.38
     enough
    1.35
     ENOUGH
    1.30
    Sufficient
    1.22
     Sufficient
    1.20
     sufficient
    1.16
    sufficient
    1.12
     fufficient
    1.09
    Act Density 0.096%

    No Known Activations