INDEX
    Explanations

    references to snack foods and desserts

    New Auto-Interp
    Negative Logits
    ‌است
    -0.54
    topus
    -0.50
     Sarkar
    -0.50
     --}}
    -0.50
     further
    -0.48
    -0.45
    printStackTrace
    -0.44
      
    -0.43
     Cowley
    -0.43
     Gau
    -0.43
    POSITIVE LOGITS
     snacks
    0.93
     snack
    0.91
     Snack
    0.88
     Snacks
    0.87
    Snacks
    0.79
    snack
    0.74
    Snack
    0.67
     crackers
    0.66
     popcorn
    0.66
     cookies
    0.66
    Act Density 0.107%

    No Known Activations