INDEX
    Explanations

    "our" and subsequent nouns

    New Auto-Interp
    Negative Logits
     должен
    0.59
     один
    0.58
     swojego
    0.58
     svoj
    0.56
     candidatura
    0.56
    0.56
     своего
    0.55
     способен
    0.54
     svůj
    0.53
     teclado
    0.52
    POSITIVE LOGITS
    ad
    0.78
     ourselves
    0.73
     আমাদের
    0.60
     наших
    0.59
    mêmes
    0.57
    ខ្ញុំ
    0.55
    larımız
    0.55
    :
    0.55
    ite
    0.54
     ہمارے
    0.54
    Act Density 0.060%

    No Known Activations