INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    araq
    -0.08
    ainted
    -0.07
     Cocoa
    -0.07
    idwa
    -0.07
     Saddle
    -0.07
    ibrary
    -0.07
    ummar
    -0.07
    ariat
    -0.07
    ervers
    -0.07
    utenant
    -0.07
    POSITIVE LOGITS
     gama
    0.08
     Δ
    0.08
    _money
    0.08
     hou
    0.08
    Finance
    0.08
    Date
    0.07
     Mund
    0.07
    0.07
     juste
    0.07
    Δ
    0.07
    Act Density 0.004%

    No Known Activations