INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ет
    -0.08
     attracted
    -0.08
    Prem
    -0.08
     עס
    -0.08
    Deaths
    -0.08
     сою
    -0.08
     associative
    -0.07
    \">
    -0.07
     alliances
    -0.07
     escape
    -0.07
    POSITIVE LOGITS
     demeanor
    0.10
     importantly
    0.09
    nias
    0.08
     amable
    0.08
     punts
    0.08
     Inspection
    0.08
    alars
    0.07
    kach
    0.07
     glance
    0.07
     ممتاز
    0.07
    Act Density 0.023%

    No Known Activations