INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     nke
    -0.08
     Cr
    -0.08
     multiline
    -0.08
     debit
    -0.08
     Patch
    -0.07
     stuff
    -0.07
    נס
    -0.07
     fuel
    -0.07
    ============
    -0.07
    BG
    -0.07
    POSITIVE LOGITS
     who've
    0.10
     interested
    0.08
     wishing
    0.08
     William
    0.08
    들에게
    0.08
    William
    0.08
    ্যাত
    0.08
     যারা
    0.08
    shot
    0.08
    权益
    0.08
    Act Density 0.035%

    No Known Activations