INDEX
    Explanations

    Titles of articles/people

    New Auto-Interp
    Negative Logits
     Efq
    -1.02
     '\\;'
    -0.98
     itſelf
    -0.98
    ſelf
    -0.96
    moiselle
    -0.94
     Roskov
    -0.94
     myſelf
    -0.92
    setVerticalGroup
    -0.91
    PreferredItem
    -0.90
     ſind
    -0.90
    POSITIVE LOGITS
    g
    0.47
    n
    0.43
    per
    0.43
    at
    0.42
    G
    0.40
     Den
    0.38
    w
    0.37
    int
    0.37
    id
    0.37
    m
    0.37
    Act Density 0.001%

    No Known Activations