INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    crt
    -0.08
     appreh
    -0.08
     Ruben
    -0.08
    âme
    -0.08
     tore
    -0.08
     horr
    -0.07
     hole
    -0.07
     reduct
    -0.07
     topical
    -0.07
     люб
    -0.07
    POSITIVE LOGITS
     Prius
    0.10
     Toyota
    0.09
     Honda
    0.08
    340
    0.08
     gurus
    0.08
     kicks
    0.08
     motorcycle
    0.08
     fluoride
    0.08
     abst
    0.08
    986
    0.07
    Act Density 0.006%

    No Known Activations