INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pouvoir
    -0.09
     propulsion
    -0.08
     train
    -0.08
     pyro
    -0.08
     λόγ
    -0.08
    _train
    -0.08
     plastique
    -0.07
    bearing
    -0.07
     propre
    -0.07
     slim
    -0.07
    POSITIVE LOGITS
     monitoring
    0.09
     Monitoring
    0.09
    Monitoring
    0.09
     alert
    0.08
    0.08
    0.08
     oscill
    0.08
    alert
    0.08
     indikator
    0.08
     apnea
    0.08
    Act Density 0.006%

    No Known Activations