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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     PARA
    -0.08
    BOR
    -0.08
    界限
    -0.07
    分区
    -0.07
    优质的
    -0.07
    阶层
    -0.07
     complain
    -0.07
     FU
    -0.07
    Winter
    -0.07
     inclus
    -0.07
    POSITIVE LOGITS
    蟮
    0.08
    깜
    0.07
    空军
    0.07
    鏖
    0.07
    짖
    0.07
    gebn
    0.07
     Rebel
    0.06
     tanto
    0.06
     dẫn
    0.06
    他妈
    0.06
    Act Density 0.009%

    No Known Activations