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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    蘩
    -0.08
     rode
    -0.07
     NO
    -0.06
     blush
    -0.06
     mắn
    -0.06
     fuck
    -0.06
    Think
    -0.06
     CONTR
    -0.06
     restore
    -0.06
    国籍
    -0.06
    POSITIVE LOGITS
    措施
    0.08
    Craig
    0.07
    scheme
    0.07
     gdyż
    0.07
    uggestion
    0.07
    'à
    0.07
    うま
    0.07
    北京市
    0.07
     advice
    0.07
    authenticate
    0.07
    Act Density 0.007%

    No Known Activations