INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Resistance
    -0.08
     он
    -0.08
     Zinc
    -0.08
    -0.08
    -0.08
     Buffalo
    -0.08
     ass
    -0.08
     Tint
    -0.08
     prettier
    -0.07
     Prism
    -0.07
    POSITIVE LOGITS
    notify
    0.09
    prime
    0.08
    partials
    0.08
    mach
    0.08
    unset
    0.08
    0.08
    0.08
     physics
    0.08
    plt
    0.08
    physics
    0.07
    Act Density 0.012%

    No Known Activations