INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    @Column
    -0.09
     outing
    -0.08
    51
    -0.08
     wise
    -0.08
    BMP
    -0.08
     чи
    -0.07
     خوا
    -0.07
    Fig
    -0.07
    (GTK
    -0.07
     presumably
    -0.07
    POSITIVE LOGITS
     amps
    0.08
     España
    0.08
     Europea
    0.08
     Knife
    0.08
    opped
    0.08
     Tutorial
    0.08
     knives
    0.08
    koper
    0.07
     Frankrijk
    0.07
     Europas
    0.07
    Act Density 0.169%

    No Known Activations