INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     भाजी
    0.93
     lymph
    0.84
     ethn
    0.84
    🍅
    0.84
     FISH
    0.83
     Aquaculture
    0.83
     Soup
    0.83
    Lymph
    0.82
    ethn
    0.81
     ethnicity
    0.81
    POSITIVE LOGITS
     cake
    2.03
     candy
    1.99
     sweets
    1.99
    🍰
    1.98
     dessert
    1.92
     desserts
    1.89
     confectionery
    1.88
    蛋糕
    1.87
     chocolate
    1.85
     sugary
    1.82
    Act Density 0.510%

    No Known Activations