INDEX
    Explanations

    references to shoes with high relevance

    references to shoes and related footwear

    New Auto-Interp
    Negative Logits
    erest
    -0.73
    itative
    -0.72
    yrinth
    -0.70
    VD
    -0.69
    uality
    -0.68
    PsyNetMessage
    -0.68
    REDACTED
    -0.68
    iversal
    -0.68
    ITIES
    -0.67
     subp
    -0.65
    POSITIVE LOGITS
     shoes
    1.16
    horn
    1.06
    bridge
    0.99
     Shoes
    0.97
    prints
    0.95
     worn
    0.93
    pee
    0.89
     socks
    0.87
    toe
    0.86
     footwear
    0.86
    Act Density 0.016%

    No Known Activations