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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the beginning of text portions

    oai_token-act-pair · gpt-3.5-turbo

    symbolic indicators and metadata within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.96
     specifications
    -0.70
     separately
    -0.67
    accompan
    -0.67
     procedures
    -0.66
     thereafter
    -0.66
     afterward
    -0.65
     configurations
    -0.65
     differences
    -0.64
    FontSize
    -0.64
    POSITIVE LOGITS
     john
    0.99
     dan
    0.95
    Anonymous
    0.92
    jon
    0.91
    mr
    0.90
     david
    0.89
     kb
    0.88
     mc
    0.88
     cz
    0.87
     adam
    0.87
    Act Density 0.118%

    No Known Activations