INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     woody
    -0.09
    bas
    -0.08
    grade
    -0.08
     waterproof
    -0.08
    학교
    -0.08
     Waterproof
    -0.07
     absorber
    -0.07
     gjerne
    -0.07
     trygg
    -0.07
     Washing
    -0.07
    POSITIVE LOGITS
     implied
    0.08
     чис
    0.08
     perpetr
    0.08
    /images
    0.07
    စား
    0.07
    Referenced
    0.07
    0.07
    862
    0.07
     ↵	↵
    0.07
     Jama
    0.07
    Act Density 0.019%

    No Known Activations