INDEX
    Explanations

    references to specific car brands

    New Auto-Interp
    Negative Logits
    arters
    -0.81
    mond
    -0.70
    atro
    -0.68
    odore
    -0.68
    mary
    -0.66
    porting
    -0.65
    tainment
    -0.65
    agents
    -0.64
    laus
    -0.63
    owder
    -0.62
    POSITIVE LOGITS
     BMW
    0.86
    sonian
    0.85
     Motorsport
    0.77
    imil
    0.76
    ied
    0.68
     Scher
    0.67
     dealership
    0.66
     ank
    0.64
    ilion
    0.63
    pillar
    0.62
    Act Density 0.004%

    No Known Activations