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

    Neuronpedia

    INDEX
    Explanations

    structured data, specifically in a JSON-like format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plainte
    -0.61
     miliardi
    -0.57
     cherchés
    -0.56
     leçon
    -0.55
     démocr
    -0.55
     financières
    -0.55
    atial
    -0.54
     muualla
    -0.52
     pleins
    -0.52
     courants
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.71
    yntaxException
    0.71
    #
    0.60
    entgen
    0.59
    TagHelper
    0.59
    <?
    0.58
     GenerationType
    0.57
    msgTypes
    0.56
    RetentionPolicy
    0.52
     ===
    0.52
    Act Density 0.295%

    No Known Activations