INDEX
    Explanations

    emotional states and expressions related to relationships and interactions

    New Auto-Interp
    Negative Logits
     dub
    -0.48
    zug
    -0.48
     dram
    -0.45
    ChangeEvent
    -0.45
    dokument
    -0.43
    dub
    -0.42
    -0.42
     meld
    -0.42
     did
    -0.42
    Dub
    -0.41
    POSITIVE LOGITS
    RectangleBorder
    0.75
     OFDb
    0.70
    Atsauces
    0.69
     saites
    0.67
    MigrationBuilder
    0.67
    AnimationsModule
    0.64
     kasarigan
    0.64
    sizeCache
    0.63
     transfieras
    0.61
     existent
    0.61
    Act Density 0.609%

    No Known Activations