INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     motto
    -0.09
     lemonade
    -0.09
     seasoning
    -0.09
     governor
    -0.09
     brewery
    -0.09
     Cocktail
    -0.08
     governance
    -0.08
     bouwen
    -0.08
    rocket
    -0.08
     beverage
    -0.08
    POSITIVE LOGITS
     imaging
    0.20
     MRI
    0.18
     ultrasound
    0.17
     Imaging
    0.16
     обслед
    0.14
     tomography
    0.14
     영상
    0.14
     diagnostic
    0.14
    MRI
    0.14
     диагност
    0.13
    Act Density 0.051%

    No Known Activations