INDEX
    Explanations

    references to different types of vehicles, specifically SUVs

    references to vehicles, particularly SUVs and similar models

    New Auto-Interp
    Negative Logits
     Napoleon
    -0.66
     dem
    -0.64
     criminal
    -0.63
     Trace
    -0.62
     wrench
    -0.62
     artist
    -0.62
     bond
    -0.62
     prejudice
    -0.61
     memory
    -0.61
     Finger
    -0.58
    POSITIVE LOGITS
    Vs
    4.44
    VS
    1.73
    vs
    1.57
    Cs
    1.41
    Bs
    1.33
    V
    1.31
     Vs
    1.31
    Ps
    1.31
    Fs
    1.28
    Rs
    1.28
    Act Density 0.009%

    No Known Activations