INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    endet
    -0.08
    DEX
    -0.08
    iesta
    -0.08
    oyo
    -0.08
    ína
    -0.08
    مت
    -0.08
    oba
    -0.08
    opo
    -0.08
    орон
    -0.08
    ENER
    -0.08
    POSITIVE LOGITS
     ph
    0.11
     Ch
    0.11
     CH
    0.11
     ch
    0.10
     Ph
    0.09
     Sh
    0.09
    Ch
    0.09
     sh
    0.09
    CH
    0.08
     sp
    0.08
    Act Density 0.329%

    No Known Activations