INDEX
    Explanations

    references to the name "Davis"

    references to specific individuals, particularly the name "Davis."

    New Auto-Interp
    Negative Logits
    Datuak
    -0.98
    gonic
    -0.83
    +#+#
    -0.83
    verwijspagina
    -0.82
    rrbracket
    -0.77
    SEVERE
    -0.74
    __*/
    -0.74
    
    -0.74
    slidesPer
    -0.73
    '},
    
    -0.73
    POSITIVE LOGITS
     Davis
    0.91
    Davis
    0.84
     DAVIS
    0.79
    davis
    0.75
     quæ
    0.73
    ity
    0.66
    son
    0.58
    मान
    0.58
     davis
    0.58
    ANIM
    0.58
    Act Density 0.039%

    No Known Activations