INDEX
    Explanations

    expressions of pride and related sentiments

    New Auto-Interp
    Negative Logits
     KF
    -0.61
    Composable
    -0.58
    worms
    -0.57
    __":
    
    -0.56
    Dior
    -0.56
    persons
    -0.55
     ergo
    -0.54
     Monks
    -0.54
    HandlerContext
    -0.54
    łaj
    -0.52
    POSITIVE LOGITS
    proud
    1.76
     proud
    1.76
     Proud
    1.70
    Proud
    1.64
     orgull
    1.60
     pride
    1.60
     stolz
    1.47
     proudly
    1.45
     orgullo
    1.40
    pride
    1.39
    Act Density 0.061%

    No Known Activations