INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    anze
    -0.08
     pdata
    -0.08
     Mere
    -0.07
    ibilities
    -0.07
     Weil
    -0.07
    -0.07
    ilis
    -0.07
     bann
    -0.07
     prüfen
    -0.07
    imeline
    -0.07
    POSITIVE LOGITS
    FP
    0.09
     philanth
    0.09
     FP
    0.09
     sustainable
    0.08
    Gig
    0.08
    Sock
    0.08
    Run
    0.07
     Perc
    0.07
     Gig
    0.07
    Ign
    0.07
    Act Density 0.037%

    No Known Activations