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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     /*#__
    -0.08
    俵
    -0.07
    auen
    -0.07
     ance
    -0.07
    슴
    -0.07
    紫
    -0.07
    بدأ
    -0.06
    umed
    -0.06
    旁
    -0.06
    ﱠ
    -0.06
    POSITIVE LOGITS
    冲击
    0.07
    arguments
    0.07
    书籍
    0.07
     Body
    0.07
    stick
    0.07
    ♟
    0.07
     StringWriter
    0.07
     automated
    0.07
     infos
    0.07
     predictions
    0.06
    Act Density 0.000%

    No Known Activations