INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     polynomial
    -0.07
     Evet
    -0.07
     examined
    -0.06
    -0.06
    allee
    -0.06
     topic
    -0.06
    icators
    -0.06
     mặt
    -0.06
     rubbed
    -0.06
     Colony
    -0.06
    POSITIVE LOGITS
     African
    0.12
     Africa
    0.11
     africa
    0.09
    frican
    0.09
    frica
    0.08
     african
    0.07
    ční
    0.07
     Africans
    0.07
    _PUBLIC
    0.06
    कर
    0.06
    Act Density 0.011%

    No Known Activations