INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    67
    -0.08
    _b
    -0.08
     colomb
    -0.07
    92
    -0.07
    86
    -0.07
     politically
    -0.06
    107
    -0.06
    日に
    -0.06
     arr
    -0.06
    -0.06
    POSITIVE LOGITS
     enterprise
    0.15
     Enterprise
    0.14
     enterprises
    0.12
    Enterprise
    0.10
     Enterprises
    0.10
    enterprise
    0.10
     предпри
    0.09
    .enterprise
    0.08
    0.08
     Hend
    0.07
    Act Density 0.010%

    No Known Activations