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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    賚
    0.45
     Zhao
    0.44
    寶寶
    0.39
    非常好
    0.39
     discrepancy
    0.38
    それぞれ
    0.38
    жение
    0.38
    何も
    0.37
    棣
    0.37
    ଲେ
    0.37
    POSITIVE LOGITS
     Tears
    0.40
     naprav
    0.40
    标准
    0.39
    Transparent
    0.39
    carta
    0.39
    manes
    0.39
     میراتھن
    0.38
     Gre
    0.38
    Ironically
    0.38
    灰
    0.37
    Act Density 0.003%

    No Known Activations