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

    Neuronpedia

    INDEX
    Explanations

    The neuron detects floating-point numeric literals (decimal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    oret
    -0.06
    Val
    -0.06
    _Row
    -0.06
    SPEC
    -0.06
    aturity
    -0.06
    Fu
    -0.06
    `()
    -0.06
     Val
    -0.06
    KA
    -0.06
    .getHeader
    -0.06
    POSITIVE LOGITS
    桌
    0.07
     grams
    0.06
     ecs
    0.06
    ابر
    0.06
    roat
    0.06
     подой
    0.06
     betting
    0.06
    _slots
    0.06
    år
    0.06
    getX
    0.06
    Act Density 0.074%

    No Known Activations