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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Compare
    -0.08
    prt
    -0.07
    (correct
    -0.07
     ";↵↵
    -0.07
     assertTrue
    -0.07
    𝛽
    -0.07
    זמן
    -0.07
     [.
    -0.07
    来这里
    -0.07
    co
    -0.07
    POSITIVE LOGITS
    embedding
    0.07
     Khánh
    0.07
     Fib
    0.07
    �
    0.07
     Tw
    0.07
     البر
    0.07
    힉
    0.07
    淏
    0.07
    /Math
    0.07
     Cast
    0.07
    Act Density 0.048%

    No Known Activations