INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pain
    -1.17
     Pain
    -1.02
     douleur
    -1.02
    Pain
    -1.01
    pain
    -1.00
     PAIN
    -0.96
     pijn
    -0.89
     douleurs
    -0.75
    الحياه
    -0.74
     боли
    -0.69
    POSITIVE LOGITS
     []:
    0.59
     gyrus
    0.56
    ographer
    0.52
    alsy
    0.50
     sche
    0.49
     condition
    0.48
     condens
    0.48
    Worker
    0.48
     Anomaly
    0.48
    ink
    0.48
    Act Density 0.083%

    No Known Activations