INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _yaw
    -0.07
    -0.07
     Си
    -0.06
    -0.06
     disabled
    -0.06
    Š
    -0.06
    magnitude
    -0.06
    レイ
    -0.06
     ```↵
    -0.06
    ратег
    -0.06
    POSITIVE LOGITS
     Premiership
    0.07
     práci
    0.06
    -user
    0.06
     sweeping
    0.06
     recruiter
    0.06
     influence
    0.06
     usually
    0.06
     cave
    0.06
     special
    0.06
    xp
    0.06
    Act Density 0.023%

    No Known Activations