INDEX
    Explanations

    references to notable individuals and their contributions in film and literature

    New Auto-Interp
    Negative Logits
     constrained
    -0.18
     famously
    -0.17
     messaging
    -0.17
     mojo
    -0.17
     tasked
    -0.17
     marginalized
    -0.17
    gender
    -0.16
     genders
    -0.16
     gender
    -0.16
     backstory
    -0.16
    POSITIVE LOGITS
     Negro
    0.21
     gadget
    0.19
     gimm
    0.17
     showdown
    0.17
     licked
    0.17
     waterfront
    0.16
     setups
    0.16
     cigaret
    0.16
     gadgets
    0.15
     breakdown
    0.15
    Act Density 0.710%

    No Known Activations