INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kurt
    -0.09
     Zent
    -0.08
    gın
    -0.08
     Kick
    -0.08
     Played
    -0.07
     lust
    -0.07
     Herr
    -0.07
    EOF
    -0.07
     Anton
    -0.07
     Ha
    -0.07
    POSITIVE LOGITS
    0.10
    0.08
    0.08
     над
    0.08
    经过
    0.08
     сир
    0.08
    0.08
    0.08
    方案
    0.08
    Rc
    0.07
    Act Density 0.010%

    No Known Activations