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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Iran
    -0.07
     brunch
    -0.07
     spare
    -0.07
     dass
    -0.06
    �
    -0.06
     noch
    -0.06
    Ms
    -0.06
    屋子
    -0.06
     lettre
    -0.06
    询问
    -0.06
    POSITIVE LOGITS
     MEP
    0.07
     Formatting
    0.07
     Cunning
    0.07
     Eval
    0.07
    \C
    0.07
     fv
    0.07
     다양
    0.07
    _STAGE
    0.07
     уме
    0.06
     HMAC
    0.06
    Act Density 0.169%

    No Known Activations