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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lãi
    -0.07
    Transition
    -0.07
     outraged
    -0.07
    كام
    -0.06
    贶
    -0.06
     cries
    -0.06
     tribe
    -0.06
     Bison
    -0.06
    唛
    -0.06
    ཡ
    -0.06
    POSITIVE LOGITS
    嘉
    0.08
     DG
    0.07
     DT
    0.07
    佩戴
    0.07
    Db
    0.07
    _bot
    0.07
    DT
    0.07
    ETER
    0.07
    MatrixMode
    0.07
     differences
    0.07
    Act Density 0.018%

    No Known Activations