INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    TIA
    -0.08
     Di
    -0.08
    امن
    -0.07
    (es
    -0.07
    ające
    -0.07
    mn
    -0.07
     manger
    -0.07
     mn
    -0.07
     Sow
    -0.07
    ymi
    -0.07
    POSITIVE LOGITS
     bored
    0.10
     yacht
    0.09
     golf
    0.09
     helmet
    0.08
     boredom
    0.08
    0.08
     adrenaline
    0.08
     pror
    0.08
     charisma
    0.08
     aggress
    0.08
    Act Density 0.003%

    No Known Activations