INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.07
    addresses
    -0.07
    כמה
    -0.07
    תם
    -0.07
    נר
    -0.07
    грам
    -0.07
     viol
    -0.07
    -0.07
     roam
    -0.06
    cef
    -0.06
    POSITIVE LOGITS
     exciting
    0.07
     legislative
    0.07
    Away
    0.07
     olan
    0.07
     Louisiana
    0.07
    HA
    0.07
     Wis
    0.07
     tyr
    0.07
     zeigen
    0.07
     detectives
    0.07
    Act Density 0.004%

    No Known Activations