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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (MPI
    -0.08
    hyp
    -0.07
    _CAP
    -0.07
     Hog
    -0.07
     Chevy
    -0.07
    .BUTTON
    -0.07
     Whe
    -0.07
    iola
    -0.06
    Ep
    -0.06
     kp
    -0.06
    POSITIVE LOGITS
    ADX
    0.08
     Arts
    0.08
    ൽ
    0.07
    (mapStateToProps
    0.07
     lexer
    0.07
    沟通
    0.07
    ائيل
    0.07
    门
    0.06
    形式
    0.06
    циальн
    0.06
    Act Density 0.006%

    No Known Activations