INDEX
    Explanations

    references to a specific individual named "Ben."

    New Auto-Interp
    Negative Logits
    сылкі
    -0.90
     itſelf
    -0.90
     ſever
    -0.90
     myſelf
    -0.83
     Lw
    -0.82
     Nestor
    -0.82
    \""
    -0.81
    »»
    -0.81
     ROE
    -0.79
     Majefty
    -0.78
    POSITIVE LOGITS
     Ben
    1.47
     BEN
    1.32
    Ben
    1.27
     ben
    1.21
     Bennet
    1.17
    BEN
    1.15
     Benav
    1.13
     للاسماء
    1.07
    ben
    1.05
     Beni
    1.01
    Act Density 0.009%

    No Known Activations