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

    Neuronpedia

    INDEX
    Explanations

    references to scaling laws and mathematical expressions in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.71
     Numerade
    -0.55
    webElementXpaths
    -0.52
    ⟬
    -0.52
    ]")]
    -0.51
    WebElementEntity
    -0.50
    cshtml
    -0.48
    messageInfo
    -0.48
     otomatig
    -0.47
    MLLoader
    -0.47
    POSITIVE LOGITS
     exponent
    0.59
     exponents
    0.59
     power
    0.52
    exponent
    0.49
    Exponent
    0.46
     degree
    0.45
     Power
    0.44
    power
    0.44
    Power
    0.43
    Degree
    0.43
    Act Density 1.891%

    No Known Activations