INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     briefing
    -0.08
     egw
    -0.08
     Eric
    -0.07
    .plugin
    -0.07
    Plugins
    -0.07
    .handlers
    -0.07
     проекта
    -0.07
    п
    -0.07
     socialize
    -0.07
     temporada
    -0.07
    POSITIVE LOGITS
    0.09
    cox
    0.08
     ign
    0.08
    0.08
    Collapse
    0.07
     Collapse
    0.07
    0.07
    mesh
    0.07
    IGNORE
    0.07
     kosong
    0.07
    Act Density 0.005%

    No Known Activations