INDEX
    Explanations

    friends, colleagues, and companions

    New Auto-Interp
    Negative Logits
    0.44
     мальчика
    0.44
     وزار
    0.39
     menino
    0.38
     OUR
    0.38
     তিনটি
    0.37
     suas
    0.37
     nasze
    0.36
    0.36
    0.36
    POSITIVE LOGITS
     friends
    2.00
     colleagues
    1.97
     peers
    1.65
    朋友
    1.63
    เพื่อน
    1.60
     colleague
    1.56
     friend
    1.55
    friends
    1.55
     companions
    1.55
     compañeros
    1.54
    Act Density 0.121%

    No Known Activations