INDEX
    Explanations

    first person pronouns

    New Auto-Interp
    Negative Logits
     улуч
    -0.07
     Following
    -0.07
    -0.07
    /show
    -0.06
    -0.06
     достав
    -0.06
    Following
    -0.06
    powered
    -0.06
     پژ
    -0.06
     Vys
    -0.06
    POSITIVE LOGITS
     하고
    0.06
    $↵
    0.06
     Champagne
    0.06
    0.06
    itre
    0.06
    عمل
    0.06
    %</
    0.06
    Rejected
    0.06
    \v
    0.06
    ěl
    0.06
    Act Density 0.050%

    No Known Activations