INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bienes
    -0.08
     surn
    -0.08
    çons
    -0.08
    -0.08
     merchants
    -0.08
    -0.08
     obdob
    -0.08
    nero
    -0.08
    19
    -0.08
     memperoleh
    -0.08
    POSITIVE LOGITS
     spoiler
    0.08
    endet
    0.08
     Integrity
    0.07
     VIS
    0.07
     thermal
    0.07
    0.07
     outage
    0.07
     integrity
    0.07
    0.07
    0.07
    Act Density 0.015%

    No Known Activations