INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     donn
    -0.08
     خط
    -0.08
    -0.08
    ther
    -0.08
    Ack
    -0.08
     Sat
    -0.07
    Quest
    -0.07
    -0.07
     Eccles
    -0.07
    probably
    -0.07
    POSITIVE LOGITS
     Miche
    0.09
     cure
    0.08
    0.08
     penetrating
    0.07
     pu
    0.07
     Philippines
    0.07
     Ds
    0.07
     sel
    0.07
     crom
    0.07
    0.07
    Act Density 0.059%

    No Known Activations