INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     dd
    -0.08
     яг
    -0.07
    _mp
    -0.07
    merchant
    -0.07
     affiliate
    -0.07
     Mushroom
    -0.07
     evid
    -0.07
     yards
    -0.07
    ovsky
    -0.07
    entered
    -0.07
    POSITIVE LOGITS
     Sarat
    0.09
    US
    0.08
     polyester
    0.08
    0.08
     outre
    0.08
     oma
    0.08
    USR
    0.07
    aho
    0.07
    0.07
     dissip
    0.07
    Act Density 0.003%

    No Known Activations