INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     vooruit
    -0.09
     ruh
    -0.09
     kòm
    -0.08
     sepanjang
    -0.08
     isin
    -0.08
     ansanm
    -0.08
     Pause
    -0.08
    pause
    -0.08
     TOTAL
    -0.07
     pause
    -0.07
    POSITIVE LOGITS
     opio
    0.08
    0.08
    pect
    0.07
    0.07
    0.07
    OGA
    0.07
     irrit
    0.07
    0.07
    .defaults
    0.07
    -induced
    0.07
    Act Density 0.004%

    No Known Activations