INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Lag
    -0.08
     bacter
    -0.08
     gegenüber
    -0.08
    lf
    -0.07
    You've
    -0.07
     boot
    -0.07
    Boot
    -0.07
     struggle
    -0.07
     enables
    -0.07
    Lag
    -0.07
    POSITIVE LOGITS
    hum
    0.08
     Pedro
    0.08
     poole
    0.08
     Jerem
    0.08
     gon
    0.08
     Parlamento
    0.08
     Kait
    0.08
     PCS
    0.08
     Maße
    0.08
     thermo
    0.07
    Act Density 0.002%

    No Known Activations