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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ACHINE
    -0.08
     producing
    -0.07
     cocktails
    -0.07
     uber
    -0.07
     Join
    -0.07
    اختبار
    -0.07
    خت
    -0.06
     crossings
    -0.06
    买入
    -0.06
     autobiography
    -0.06
    POSITIVE LOGITS
    只要
    0.07
     LGPL
    0.07
     limited
    0.06
    lıkl
    0.06
    励
    0.06
    貔
    0.06
     Harr
    0.06
     Tablets
    0.06
    .getItems
    0.06
    军
    0.06
    Act Density 0.004%

    No Known Activations