INDEX
    Explanations

    the word "But" indicating a contrast or shift in thought

    contrasting ideas after 'but'

    New Auto-Interp
    Negative Logits
     vicinity
    -0.48
    AKS
    -0.43
     Lagoon
    -0.43
    ioneta
    -0.42
    OMO
    -0.42
     recreate
    -0.42
    vermögen
    -0.42
    }{||
    -0.42
     ویکی‌پدی
    -0.41
     entirety
    -0.41
    POSITIVE LOGITS
     But
    1.34
    But
    1.27
    Nhưng
    0.81
    Doch
    0.78
     Nhưng
    0.77
     Tetapi
    0.74
     但
    0.73
    Tetapi
    0.71
     BUT
    0.71
     Doch
    0.70
    Act Density 0.023%

    No Known Activations