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

    Neuronpedia

    INDEX
    Explanations

    specific structural elements or tokens in a coding context, particularly involving data queries and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InitVars
    -0.70
    featureID
    -0.58
    nsic
    -0.55
     modern
    -0.54
    Browsable
    -0.52
    guarding
    -0.52
    necedor
    -0.52
    ScopeManager
    -0.52
    Twig
    -0.51
     development
    -0.50
    POSITIVE LOGITS
    ftagPool
    0.78
     للمعارف
    0.70
     onOptions
    0.70
     дописавши
    0.68
     متعلقه
    0.67
    findpost
    0.58
    !*\
    0.55
    withIdentifier
    0.53
    Rüyada
    0.53
    脚注の使い方
    0.51
    Act Density 0.272%

    No Known Activations