INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     прог
    -0.10
    IRONMENT
    -0.09
     Sab
    -0.09
    -0.08
    Sab
    -0.08
    -0.07
    school
    -0.07
     sab
    -0.07
     Gang
    -0.07
    -0.07
    POSITIVE LOGITS
    0.08
    mst
    0.07
     kre
    0.07
     Leo
    0.07
    ners
    0.07
    -industr
    0.07
     Luna
    0.07
     PERF
    0.07
     Gordon
    0.07
     trolling
    0.07
    Act Density 0.021%

    No Known Activations