INDEX
    Explanations

    Names in story prompts

    New Auto-Interp
    Negative Logits
     multipl
    -0.08
     multiplier
    -0.08
    onomic
    -0.08
    ullar
    -0.08
     تعليق
    -0.08
     contaminants
    -0.07
     Monopoly
    -0.07
    closing
    -0.07
    က
    -0.07
    ರ್ಗ
    -0.07
    POSITIVE LOGITS
     surn
    0.09
     అనే
    0.08
     Shades
    0.08
    XYZ
    0.08
    GRAY
    0.08
    名字
    0.08
     âg
    0.08
     Doe
    0.08
    0.08
    Sunny
    0.08
    Act Density 0.059%

    No Known Activations