INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    in
    1.50
    the
    1.34
    an
    1.16
    a
    1.14
    ın
    1.03
    st
    1.01
    u
    1.00
    t
    1.00
    g
    1.00
    .
    0.99
    POSITIVE LOGITS
    ك
    0.87
     Și
    0.75
    كور
    0.73
     
    0.73
    -
    0.73
    0.73
    ennzeichnet
    0.71
     Anzahl
    0.71
     Ekonom
    0.70
    كبر
    0.70
    Act Density 0.007%

    No Known Activations