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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     richness
    -0.07
    LOB
    -0.07
    APT
    -0.07
    该剧
    -0.07
    此事
    -0.06
    长达
    -0.06
     pinpoint
    -0.06
    貝
    -0.06
    缱
    -0.06
    UN
    -0.06
    POSITIVE LOGITS
     Asians
    0.08
     prefers
    0.07
     SEAL
    0.07
    _transaksi
    0.07
    яет
    0.07
    힘
    0.07
    聊城
    0.07
    흔
    0.07
     acid
    0.07
    醚
    0.07
    Act Density 0.004%

    No Known Activations