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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    PS
    -0.09
    @register
    -0.07
     קנ
    -0.07
    cence
    -0.07
     einige
    -0.07
     economic
    -0.07
     bfs
    -0.07
     CS
    -0.07
     BDS
    -0.07
    쫀
    -0.07
    POSITIVE LOGITS
    য
    0.07
     wah
    0.07
     Jew
    0.07
    فق
    0.07
    出汗
    0.07
     DAO
    0.07
    ��이
    0.07
    教堂
    0.07
    ([])↵
    0.07
    ῆ
    0.07
    Act Density 0.005%

    No Known Activations