INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     мил
    -0.07
     david
    -0.07
    Ind
    -0.07
    (':
    -0.07
    Fond
    -0.07
    -ind
    -0.07
     sau
    -0.07
     дизайн
    -0.07
     Dominion
    -0.07
    Correspond
    -0.07
    POSITIVE LOGITS
     thes
    0.09
     Kef
    0.08
     Pat
    0.08
     Tes
    0.08
     ves
    0.07
     Ram
    0.07
     Dess
    0.07
     eth
    0.07
     Gord
    0.07
     Eus
    0.07
    Act Density 0.001%

    No Known Activations