INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     fasting
    -0.08
     attent
    -0.08
     attentive
    -0.07
     aspek
    -0.07
     monit
    -0.07
     rash
    -0.07
     sorting
    -0.07
    vare
    -0.07
     haver
    -0.07
    usher
    -0.07
    POSITIVE LOGITS
    bundle
    0.08
     airplane
    0.08
    Occurrences
    0.08
    quoted
    0.08
    PNG
    0.08
    Bundle
    0.08
    sprite
    0.08
     Sprite
    0.08
     bundle
    0.08
    Bottle
    0.08
    Act Density 0.003%

    No Known Activations