INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    aku
    -0.07
     Rodrig
    -0.07
     кур
    -0.07
    (hour
    -0.06
     çerçev
    -0.06
    owards
    -0.06
     jouer
    -0.06
    -hour
    -0.06
     inquire
    -0.06
    “There
    -0.06
    POSITIVE LOGITS
     metal
    0.11
     Metal
    0.10
    Metal
    0.09
     metals
    0.08
    -metal
    0.08
    0.07
     metallic
    0.07
    steel
    0.07
     pozisyon
    0.07
     music
    0.07
    Act Density 0.016%

    No Known Activations