INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    OT
    -0.08
    <T
    -0.07
    (app
    -0.07
     evenly
    -0.07
    (Build
    -0.07
    -0.07
    (context
    -0.06
    应用
    -0.06
     Fabio
    -0.06
    <
    -0.06
    POSITIVE LOGITS
     psychologie
    0.08
     psychos
    0.08
     educational
    0.08
     offshore
    0.08
     education
    0.08
     πρό
    0.08
     nascer
    0.08
     Nguyễn
    0.08
     psih
    0.08
    dge
    0.08
    Act Density 0.001%

    No Known Activations