INDEX
    Explanations

    mentions of labor-related issues and factory closures

    New Auto-Interp
    Negative Logits
    ьаж
    -0.67
     NSCoder
    -0.63
    RetentionPolicy
    -0.60
    ēr
    -0.57
    twimg
    -0.56
    achting
    -0.54
     PopupWindow
    -0.54
     autorytatywna
    -0.54
     CascadeType
    -0.53
    WriteBarrier
    -0.51
    POSITIVE LOGITS
     factory
    1.73
     factories
    1.72
     manufacturing
    1.47
     plant
    1.43
     production
    1.42
     Factories
    1.42
    factory
    1.39
     Factory
    1.37
     plants
    1.37
    factories
    1.34
    Act Density 0.555%

    No Known Activations