INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    omy
    -0.08
    -0.07
     comerc
    -0.07
    water
    -0.07
     milyon
    -0.07
     hiding
    -0.07
    mino
    -0.07
     pixels
    -0.07
     bol
    -0.07
     tropical
    -0.07
    POSITIVE LOGITS
     покол
    0.10
    angk
    0.08
     igbes
    0.08
     takeover
    0.08
     basada
    0.08
     koe
    0.08
     inert
    0.08
    ahanan
    0.08
    0.08
    0.08
    Act Density 0.001%

    No Known Activations