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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     misery
    -0.08
    糖尿
    -0.07
    _spaces
    -0.07
     Palo
    -0.07
     nhà
    -0.07
    <Data
    -0.07
    فا
    -0.07
    _inf
    -0.06
     Очень
    -0.06
     dra
    -0.06
    POSITIVE LOGITS
    去掉
    0.08
    岞
    0.08
     стор
    0.07
    躍
    0.07
     provocative
    0.07
    -hidden
    0.07
    ניס
    0.07
     Gaga
    0.06
    鸡蛋
    0.06
    捌
    0.06
    Act Density 0.089%

    No Known Activations