INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     учнів
    -0.07
    ngoing
    -0.07
     famine
    -0.06
     Libert
    -0.06
    Obsolete
    -0.06
     역사
    -0.06
    -income
    -0.06
    收入
    -0.06
     deepen
    -0.06
     legitimacy
    -0.06
    POSITIVE LOGITS
     spray
    0.17
     Spray
    0.13
     sprayed
    0.11
     spraying
    0.11
    pray
    0.10
    ray
    0.07
    contin
    0.07
    pez
    0.07
     commercially
    0.07
    Spread
    0.06
    Act Density 0.004%

    No Known Activations