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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    룀
    -0.07
     مركز
    -0.06
     bağl
    -0.06
     carrying
    -0.06
    namespace
    -0.06
    aul
    -0.06
    串联
    -0.06
    謀
    -0.06
     Compact
    -0.06
    rique
    -0.06
    POSITIVE LOGITS
    痊
    0.07
     ding
    0.07
    硕士研究
    0.07
    かなり
    0.07
    情绪
    0.07
     annoyance
    0.07
     Dor
    0.07
    โหล
    0.07
     fout
    0.06
    gend
    0.06
    Act Density 0.001%

    No Known Activations