INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     yn
    -0.10
     y
    -0.09
     OS
    -0.09
     Aggregate
    -0.09
     Y
    -0.08
     Lem
    -0.08
     os
    -0.08
     τ
    -0.08
     Ba
    -0.08
     να
    -0.08
    POSITIVE LOGITS
    texture
    0.14
    textures
    0.13
    concept
    0.13
    fiction
    0.13
    cute
    0.12
    hyper
    0.12
    beautiful
    0.12
    pixel
    0.12
    pokemon
    0.12
    Fantasy
    0.12
    Act Density 0.011%

    No Known Activations