INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     hug
    -0.07
     LogManager
    -0.07
    Gain
    -0.07
    .HOUR
    -0.07
     Буд
    -0.06
     hugs
    -0.06
     För
    -0.06
     Anton
    -0.06
     Clayton
    -0.06
     log
    -0.06
    POSITIVE LOGITS
     recipe
    0.12
     recipes
    0.10
     Recipes
    0.09
     рецепт
    0.08
     Recipe
    0.08
     recept
    0.08
    Recipe
    0.08
    .recipe
    0.08
    0.08
    0.07
    Act Density 0.008%

    No Known Activations