INDEX
    Explanations

    references to individuals, specifically instances of the name "Jones."

    New Auto-Interp
    Negative Logits
    PhysRevD
    -0.53
    sizeCache
    -0.50
     gynhyrchwyd
    -0.48
     vroeger
    -0.45
     NUKAT
    -0.43
     Autorisations
    -0.42
     réfugiés
    -0.42
    katapos
    -0.42
     informacija
    -0.40
     technische
    -0.40
    POSITIVE LOGITS
     Jones
    0.71
     JONES
    0.66
    Jones
    0.65
     jones
    0.64
     trou
    0.55
    Slf
    0.53
     Hoo
    0.53
     ward
    0.51
    jones
    0.50
    ā
    0.49
    Act Density 1.377%

    No Known Activations