INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ka
    1.22
    Kas
    1.18
    bak
    1.15
     Ka
    1.14
     Lithuania
    1.10
     Whitley
    1.08
     Kas
    1.06
    KA
    1.05
     kara
    1.04
     ka
    1.04
    POSITIVE LOGITS
     Fred
    0.99
    Fred
    0.94
    fred
    0.81
     fixed
    0.80
     Med
    0.79
     Goddard
    0.76
     Fixed
    0.74
     Fix
    0.73
     fix
    0.72
    med
    0.70
    Act Density 2.184%

    No Known Activations