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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Grant
    -0.07
    .apple
    -0.07
    这辈子
    -0.07
    .python
    -0.07
    致富
    -0.07
     Copyright
    -0.07
     inorder
    -0.07
    (object
    -0.06
    \Bundle
    -0.06
     cà
    -0.06
    POSITIVE LOGITS
    ulled
    0.08
     humiliation
    0.07
    學
    0.07
     permite
    0.07
    הרשמה
    0.07
     agreed
    0.07
    IA
    0.07
     callee
    0.07
     кол
    0.07
    SED
    0.07
    Act Density 0.001%

    No Known Activations