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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    一件事情
    -0.07
     Producto
    -0.07
     어�
    -0.06
    ウェ
    -0.06
    什么事情
    -0.06
    ному
    -0.06
    石头
    -0.06
     junge
    -0.06
    itet
    -0.06
     Executor
    -0.06
    POSITIVE LOGITS
    IDA
    0.07
     perform
    0.07
    还原
    0.07
     behaviour
    0.07
    polation
    0.07
     Clamp
    0.07
     privat
    0.07
    �
    0.07
    ==='
    0.07
    昆山
    0.07
    Act Density 0.001%

    No Known Activations