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

    Neuronpedia

    INDEX
    Explanations

    metadata-related terms and references in text

    oai_token-act-pair · gpt-3.5-turbo

    references to data collection and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.84
    ggle
    -0.74
    awar
    -0.73
    atan
    -0.71
    ================================================================
    -0.71
     Pyth
    -0.68
    undai
    -0.68
    irth
    -0.67
    sole
    -0.66
    san
    -0.66
    POSITIVE LOGITS
     metadata
    1.06
    adata
    1.02
    metadata
    1.01
    ãĤ´
    0.79
     databases
    0.74
     tags
    0.72
     data
    0.71
     tagging
    0.71
     Flickr
    0.69
     retrieval
    0.69
    Act Density 0.007%

    No Known Activations