INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     pathogenic
    0.50
     blobs
    0.46
     abstracto
    0.45
     berfungsi
    0.44
    gebras
    0.44
     scler
    0.44
     bureaucr
    0.44
     사람들이
    0.43
     gobiernos
    0.43
     substr
    0.43
    POSITIVE LOGITS
     sophomore
    0.83
     freshman
    0.79
     Sophomore
    0.77
     Freshman
    0.71
     midfielder
    0.65
     teammate
    0.65
     offensively
    0.64
     classmate
    0.62
     freshmen
    0.60
     goalkeeper
    0.59
    Act Density 0.001%

    No Known Activations