INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    брь
    -0.82
     babi
    -0.80
    eraard
    -0.80
     sandstones
    -0.77
    kirchen
    -0.76
    安排
    -0.76
    -0.76
     Stool
    -0.75
    ariales
    -0.75
     tradiciones
    -0.75
    POSITIVE LOGITS
     bins
    1.39
     disposal
    1.37
     bin
    1.34
     Disposal
    1.26
     heap
    1.23
     collector
    1.20
    bin
    1.18
     collectors
    1.13
     Collector
    1.07
    Disposal
    1.07
    Act Density 0.015%

    No Known Activations