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

    Neuronpedia

    INDEX
    Explanations

    references to square geometric shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    揄
    -0.48
    참고
    -0.48
     ویکی‌پدی
    -0.45
    thrift
    -0.43
     After
    -0.42
    HomeAsUpEnabled
    -0.42
    Leben
    -0.42
     Udo
    -0.42
    helin
    -0.41
    inSlope
    -0.41
    POSITIVE LOGITS
     square
    1.68
     Square
    1.61
     SQUARE
    1.53
    Square
    1.53
    square
    1.45
    SQUARE
    1.41
     squares
    1.38
     Squares
    1.23
    quare
    1.22
    Squares
    1.20
    Act Density 0.295%

    No Known Activations