INDEX
    Explanations

    expressions of disapproval or negative reactions

    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.57
    PageFactory
    -0.50
    AccessorTable
    -0.49
    nologue
    -0.49
    ModelSerializer
    -0.48
     BoxFit
    -0.48
    RunWith
    -0.48
     SAA
    -0.47
    ExtendWith
    -0.47
     Gea
    -0.47
    POSITIVE LOGITS
     frown
    1.58
     frowned
    1.49
     frowns
    1.48
     frowning
    1.42
     scow
    0.75
    frow
    0.74
    皱眉
    0.70
     frow
    0.65
    Smile
    0.61
     Stirn
    0.61
    Act Density 0.005%

    No Known Activations