INDEX
    Explanations

    proper nouns or names

    New Auto-Interp
    Negative Logits
     Sparkle
    -0.67
     Sussex
    -0.64
    Ĥª
    -0.63
     Spurs
    -0.62
     Franch
    -0.62
     Despair
    -0.60
     listening
    -0.59
    ãĥ¢
    -0.59
    INC
    -0.57
     Stamford
    -0.56
    POSITIVE LOGITS
    arette
    1.33
    gers
    1.29
    arettes
    1.24
    gered
    1.23
    abyte
    1.18
    glers
    1.15
    rams
    1.15
    raphic
    1.09
    ging
    1.08
    gy
    1.07
    Act Density 0.037%

    No Known Activations