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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ainer
    -0.07
     Downs
    -0.07
    _var
    -0.07
    推理
    -0.07
    (Runtime
    -0.07
    搬运
    -0.06
     Homepage
    -0.06
     lar
    -0.06
    联合
    -0.06
    农
    -0.06
    POSITIVE LOGITS
    谇
    0.07
    ords
    0.07
    value
    0.07
     Об
    0.06
    دخل
    0.06
    的说法
    0.06
    ąd
    0.06
    ༎
    0.06
    aits
    0.06
    [np
    0.06
    Act Density 0.001%

    No Known Activations