INDEX
    Explanations

    expressions of excitement or strong emotions

    Emphasizing interjections or strong opinions

    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.05
     '\\;'
    -1.04
    
    -0.96
    ^(@)
    -0.90
     continúas
    -0.88
     EconPapers
    -0.85
     Majefty
    -0.85
     Reſ
    -0.84
    reportWebVitals
    -0.82
     pleaſure
    -0.82
    POSITIVE LOGITS
     literally
    0.75
     fucking
    0.70
     omg
    0.67
     idk
    0.63
    Omg
    0.62
    literally
    0.62
     literalmente
    0.61
     FUCKING
    0.59
    Literally
    0.58
     honestly
    0.58
    Act Density 0.102%

    No Known Activations