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

    Neuronpedia

    INDEX
    Explanations

    references to experimental research and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.66
    Smarty
    -0.66
    RuleContext
    -0.62
     kaarangay
    -0.61
    RSpec
    -0.55
    cydow
    -0.55
    forName
    -0.55
    OrEqualTo
    -0.53
    oluble
    -0.53
    LayoutStyle
    -0.53
    POSITIVE LOGITS
     unum
    0.62
    stawa
    0.61
     chré
    0.59
     ogrodow
    0.59
     reafon
    0.59
    oração
    0.59
     acrylique
    0.58
     mergeFrom
    0.58
     fevere
    0.57
     tră
    0.57
    Act Density 0.099%

    No Known Activations