INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     myš
    -0.06
    -0.06
     прож
    -0.06
    })();
    -0.06
    jších
    -0.06
     §§
    -0.06
    -0.06
    ,q
    -0.06
     cn
    -0.06
     grund
    -0.06
    POSITIVE LOGITS
     you
    0.14
     YOU
    0.09
    -you
    0.09
     You
    0.09
    you
    0.08
    You
    0.08
    YOU
    0.08
     BYU
    0.07
     dich
    0.07
     willing
    0.07
    Act Density 0.065%

    No Known Activations