INDEX
    Explanations

    emoji symbols and specific characters often used in text and social media communication

    New Auto-Interp
    Negative Logits
     Whitman
    -0.75
     Pug
    -0.69
     trickle
    -0.68
     Bain
    -0.66
     Gillespie
    -0.64
     Salem
    -0.64
    ioned
    -0.64
     Manit
    -0.63
     gloom
    -0.62
     Cass
    -0.62
    POSITIVE LOGITS
    ðŁ
    1.43
    ¥ŀ
    1.26
     ðŁ
    1.18
    ĵĺ
    1.17
    į
    1.03
    wcsstore
    1.02
    ðŁij
    1.01
     ðŁij
    0.98
    ĩ
    0.95
    ĵ
    0.94
    Act Density 0.005%

    No Known Activations