INDEX
    Explanations

    mentions of the name "Alex" and its variations

    New Auto-Interp
    Negative Logits
    /*---
    -0.52
    OGND
    -0.49
    ClientSize
    -0.48
    findpost
    -0.48
    -0.47
    AddTagHelper
    -0.46
    OCCURRED
    -0.42
    uckoo
    -0.42
    ouage
    -0.41
     يتيمه
    -0.40
    POSITIVE LOGITS
     Alex
    0.78
    Alex
    0.67
     alex
    0.64
     ALEX
    0.64
     Alexand
    0.62
    alex
    0.56
    ALEX
    0.49
    ANDER
    0.48
    Alexand
    0.48
     Alexander
    0.47
    Act Density 0.137%

    No Known Activations