INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bush
    -0.08
     resort
    -0.08
     convinc
    -0.08
     innov
    -0.08
    roc
    -0.07
     sonn
    -0.07
    ıc
    -0.07
    inus
    -0.07
    _SOC
    -0.07
     hau
    -0.07
    POSITIVE LOGITS
    0.08
     kolm
    0.08
     polisi
    0.08
     Episc
    0.08
    0.08
    .motor
    0.08
    kamera
    0.08
     Polisi
    0.07
    Facts
    0.07
     перем
    0.07
    Act Density 0.001%

    No Known Activations