INDEX
    Explanations

    references to vehicles, specifically vans

    mentions of vans and related terminology

    New Auto-Interp
    Negative Logits
     lawy
    -0.67
     Jagu
    -0.63
     charism
    -0.62
     incorpor
    -0.60
     stride
    -0.58
    TextColor
    -0.58
     Emin
    -0.55
     Sacrament
    -0.55
     Flavoring
    -0.55
     Armen
    -0.55
    POSITIVE LOGITS
    cher
    1.04
    ulators
    0.99
    ultimate
    0.98
    ulator
    0.95
    nor
    0.93
    sel
    0.91
    mers
    0.91
    der
    0.89
    ting
    0.89
    puter
    0.89
    Act Density 0.399%

    No Known Activations