INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pancakes
    -0.09
     pancake
    -0.09
     knob
    -0.08
    mits
    -0.08
     pyst
    -0.08
     pinch
    -0.08
     fri
    -0.08
     nost
    -0.08
     notch
    -0.08
     punct
    -0.08
    POSITIVE LOGITS
    hips
    0.08
    0.08
     lifecycle
    0.08
     生命周期
    0.08
     resultat
    0.08
    .Object
    0.08
    -oriented
    0.08
     sexual
    0.08
    Rpt
    0.08
    生命周期
    0.08
    Act Density 0.008%

    No Known Activations