INDEX
    Explanations

    Political party comes to power

    New Auto-Interp
    Negative Logits
     Metals
    -0.07
     Architecture
    -0.07
    会议
    -0.07
     engineered
    -0.07
    essages
    -0.06
     colors
    -0.06
     Flutter
    -0.06
     collapsed
    -0.06
     starred
    -0.06
     gelişim
    -0.06
    POSITIVE LOGITS
    ...]
    0.07
    ordo
    0.07
    
    0.06
     hry
    0.06
     UNITY
    0.06
    vocab
    0.06
     oblivious
    0.06
     stuck
    0.06
     vind
    0.06
     plage
    0.06
    Act Density 0.036%

    No Known Activations