INDEX
    Explanations

    science fiction books

    New Auto-Interp
    Negative Logits
     mj
    -0.08
    -0.08
     splash
    -0.08
     decis
    -0.08
     fem
    -0.07
     spray
    -0.07
    jos
    -0.07
     generous
    -0.07
     martial
    -0.07
     ATS
    -0.07
    POSITIVE LOGITS
    _OB
    0.08
     vigilance
    0.08
    _TEXTURE
    0.08
    wf
    0.08
    slam
    0.08
    _SL
    0.08
    _TR
    0.08
    _VAR
    0.08
    Ns
    0.07
     Holmes
    0.07
    Act Density 0.089%

    No Known Activations