INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     Chiefs
    -0.08
     cavern
    -0.07
     Bollywood
    -0.07
     Salman
    -0.07
     herald
    -0.07
     Wann
    -0.07
     сообщ
    -0.07
     איש
    -0.07
    unset
    -0.07
    POSITIVE LOGITS
     oxid
    0.11
     peroxide
    0.10
     oxidative
    0.09
    ioxid
    0.09
    0.09
    Sul
    0.08
    dam
    0.08
    very
    0.08
     oxidation
    0.08
     سول
    0.08
    Act Density 0.011%

    No Known Activations