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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     and
    -2.23
     umożli
    -1.43
    ترنت
    -1.40
    ellants
    -1.37
     '>=
    -1.36
    müller
    -1.32
    的一切
    -1.31
    чном
    -1.30
     王子
    -1.29
     gaussian
    -1.28
    POSITIVE LOGITS
     almohada
    1.55
     encantador
    1.48
    became
    1.48
     dlaczego
    1.43
    selbe
    1.43
     decidi
    1.41
    soaked
    1.41
     típico
    1.41
    越高
    1.39
    比如说
    1.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.