INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Pu
    -0.08
     impetus
    -0.08
    Vent
    -0.08
    bp
    -0.07
     kut
    -0.07
    Kal
    -0.07
    fact
    -0.07
    Kai
    -0.07
     footprint
    -0.07
    Vos
    -0.07
    POSITIVE LOGITS
    0.08
     بن
    0.08
     Len
    0.08
     starch
    0.07
     SAD
    0.07
     bunch
    0.07
    0.07
     Sad
    0.07
    0.07
     теч
    0.07
    Act Density 0.032%

    No Known Activations