INDEX
    Explanations

    words related to food, particularly specific types of sandwiches and their ingredients

    New Auto-Interp
    Negative Logits
     Eſ
    -0.69
     ſte
    -0.66
     Efq
    -0.66
     ſtate
    -0.65
     pinulongan
    -0.62
     ſeveral
    -0.62
     Heere
    -0.61
     cauſe
    -0.60
     Diſ
    -0.60
     perfons
    -0.59
    POSITIVE LOGITS
     bread
    1.31
     sandwich
    1.11
     Bread
    1.11
     sandwiches
    1.09
    🍞
    1.08
    bread
    1.05
     Sandwich
    1.05
    Bread
    1.04
     toast
    1.03
    Sandwich
    1.02
    Act Density 0.112%

    No Known Activations