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

    Neuronpedia

    INDEX
    Explanations

    references to styles and formatting in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }))
    -1.02
    sizeCache
    -1.01
    
    -1.00
    __':
    -0.95
    Captor
    -0.92
    parsedMessage
    -0.90
     CanadaChoose
    -0.90
     CSRF
    -0.89
    __':
    -0.89
    InSection
    -0.88
    POSITIVE LOGITS
     styles
    1.57
     Style
    1.52
     Styles
    1.50
     STYLE
    1.48
     style
    1.48
    Style
    1.42
    STYLE
    1.41
    style
    1.27
    Styles
    1.26
    styles
    1.25
    Act Density 0.032%

    No Known Activations