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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    리의
    0.97
     вашего
    0.88
    にとって
    0.86
     данного
    0.85
    Your
    0.84
    今回の
    0.82
     моего
    0.82
     sebuah
    0.82
     olmayan
    0.82
    其中的
    0.81
    POSITIVE LOGITS
     they
    4.40
     они
    3.75
    they
    3.64
    他们
    3.34
     вони
    3.28
     They
    3.25
     họ
    3.07
    They
    3.05
     he
    3.04
     THEY
    3.02
    Act Density 4.190%

    No Known Activations