INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    🌮
    0.93
     Protein
    0.91
     tofu
    0.91
     hummus
    0.90
    Protein
    0.84
     protein
    0.82
     tortilla
    0.81
     smoothie
    0.79
     Proteins
    0.77
     mozz
    0.76
    POSITIVE LOGITS
     Yorkshire
    0.74
     Staffordshire
    0.73
     Grandmother
    0.72
     baked
    0.72
     Baked
    0.69
    Christmas
    0.68
     grandfather
    0.68
    Baked
    0.68
     мере
    0.68
     הולנד
    0.68
    Act Density 0.159%

    No Known Activations