INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Inspection
    -0.07
     crap
    -0.06
     sprinkle
    -0.06
     bear
    -0.06
    _compiler
    -0.06
    ificial
    -0.06
    -0.06
     Vista
    -0.06
     tree
    -0.06
     categoryName
    -0.06
    POSITIVE LOGITS
     motivated
    0.11
     motivation
    0.10
     motivate
    0.10
    Mot
    0.08
     mlad
    0.07
     motivations
    0.07
     Mot
    0.07
    .op
    0.07
     мот
    0.07
     motivating
    0.07
    Act Density 0.014%

    No Known Activations