INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     более
    -0.07
    cht
    -0.07
    .model
    -0.07
     dio
    -0.07
     Heights
    -0.07
    (camera
    -0.06
    \Block
    -0.06
    iciency
    -0.06
    -0.06
     xx
    -0.06
    POSITIVE LOGITS
     ESPN
    0.19
    ESPN
    0.16
     журн
    0.07
    ZN
    0.07
     Disney
    0.07
     cooperating
    0.06
    ans
    0.06
    0.06
     MSNBC
    0.06
     immutable
    0.06
    Act Density 0.001%

    No Known Activations