INDEX
    Explanations

    mentions of specific player names and their associations in sports contexts

    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.61
    -0.49
    orsese
    -0.46
    ChildScrollView
    -0.46
    tagHelperRunner
    -0.45
     الحره
    -0.43
     nargin
    -0.43
    phism
    -0.43
    dificio
    -0.43
     Infórmanos
    -0.42
    POSITIVE LOGITS
     Serena
    0.84
    Serena
    0.78
     Williams
    0.57
    WireFormat
    0.49
    Williams
    0.48
     WILLIAMS
    0.47
    CPtr
    0.46
    HasBeenSet
    0.44
    expandindo
    0.43
     williams
    0.40
    Act Density 0.005%

    No Known Activations