INDEX
    Explanations

    names and terms related to horse racing and equestrian events

    New Auto-Interp
    Negative Logits
    roat
    -0.16
     Tar
    -0.14
    angelo
    -0.14
     Glover
    -0.13
    Ĥ
    -0.13
    oot
    -0.13
    FY
    -0.13
    bart
    -0.13
    bove
    -0.13
    DEX
    -0.13
    POSITIVE LOGITS
    eview
    0.15
    orb
    0.14
    alchemy
    0.14
    USH
    0.14
    eydi
    0.14
    ush
    0.14
    ekt
    0.14
    .registry
    0.13
     architekt
    0.13
    ednou
    0.13
    Act Density 0.012%

    No Known Activations