INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     gest
    -0.08
    -0.08
    MN
    -0.07
    ova
    -0.07
     grá
    -0.07
     foundations
    -0.07
     Fundament
    -0.07
     electrom
    -0.07
    ولوج
    -0.07
    ummers
    -0.07
    POSITIVE LOGITS
     shafts
    0.09
    0.08
     évent
    0.08
     pneumatic
    0.08
     мощ
    0.08
    situ
    0.08
     cones
    0.08
    -spe
    0.08
    119
    0.08
    ting
    0.07
    Act Density 0.002%

    No Known Activations