INDEX
    Explanations

    pronouns, possessives, and their associated nouns

    New Auto-Interp
    Negative Logits
     YOUR
    0.55
    各位
    0.47
    ACG
    0.47
     તમે
    0.47
    Your
    0.46
    0.46
     your
    0.45
    咱们
    0.44
     Chromebook
    0.44
     તમારા
    0.44
    POSITIVE LOGITS
     había
    0.55
     उसने
    0.50
    이었다
    0.50
     ඔහු
    0.49
     him
    0.49
     postwar
    0.48
     tinha
    0.48
     biographer
    0.48
     indign
    0.48
    ಲಾಯಿತು
    0.48
    Act Density 0.007%

    No Known Activations