INDEX
    Explanations

    expressions related to mathematical and computational functions

    New Auto-Interp
    Negative Logits
    twimg
    -0.57
     שוליים
    -0.50
    ſelf
    -0.45
    %;
    
    -0.44
     ſta
    -0.43
    -};
    -0.43
     panel
    -0.43
     canary
    -0.42
    jPanel
    -0.42
    Gön
    -0.42
    POSITIVE LOGITS
     indirectly
    0.57
    contentLoaded
    0.54
     indirec
    0.48
     through
    0.47
     indirect
    0.46
     overall
    0.42
    indirect
    0.40
    Indirect
    0.40
    angliski
    0.40
    Overall
    0.40
    Act Density 1.078%

    No Known Activations