Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    我的
    0.76
     minha
    0.75
     minhas
    0.75
     my
    0.75
     moje
    0.73
     of
    0.71
     моего
    0.69
    我们的
    0.68
     our
    0.68
     моих
    0.67
    POSITIVE LOGITS
    enaries
    0.65
     లే
    0.61
     reciproc
    0.61
    是你
    0.59
    ırd
    0.59
    enary
    0.58
    जानकारी
    0.58
    idey
    0.58
    etary
    0.56
    ম্পতি
    0.56
    Act Density 0.059%

    No Known Activations