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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (bb
    -0.08
    -eff
    -0.07
    嬉
    -0.07
    还有一些
    -0.07
    .Enqueue
    -0.07
    gere
    -0.07
     Cardiff
    -0.07
    🤡
    -0.07
    삻
    -0.07
    .bold
    -0.07
    POSITIVE LOGITS
    sal
    0.06
     pathology
    0.06
    /************************************************************************
    0.06
    Women
    0.06
    change
    0.06
     חול
    0.06
    angel
    0.06
    agen
    0.06
    👚
    0.06
    �
    0.06
    Act Density 0.065%

    No Known Activations