INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    leben
    -0.09
    bdd
    -0.08
     geben
    -0.08
     prazer
    -0.08
    -0.08
    vu
    -0.08
    iniai
    -0.08
    -0.08
    wissen
    -0.08
     vorz
    -0.08
    POSITIVE LOGITS
     resemblance
    0.12
    0.08
     reminiscent
    0.08
     convinc
    0.08
    Pattern
    0.08
    -threatening
    0.08
     شب
    0.08
    0.08
     striking
    0.07
     patterns
    0.07
    Act Density 0.033%

    No Known Activations