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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    荫
    -0.07
     lowers
    -0.06
    ma
    -0.06
    只
    -0.06
    ้
    -0.06
    缆
    -0.06
    朵
    -0.06
    gart
    -0.06
    ivor
    -0.06
    .fit
    -0.06
    POSITIVE LOGITS
    ธา
    0.07
    今日は
    0.07
    Moreover
    0.07
    あと
    0.07
    率为
    0.07
    되었다
    0.07
    enchmark
    0.07
    อะไร
    0.07
    WRAPPER
    0.06
     такой
    0.06
    Act Density 0.002%

    No Known Activations