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

    Neuronpedia

    INDEX
    Explanations

    travel destinations or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, particularly affluent areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emic
    -0.84
    ebook
    -0.73
    ery
    -0.73
    ering
    -0.72
     textbooks
    -0.70
     resc
    -0.68
    ered
    -0.66
    ERC
    -0.65
    err
    -0.65
    ogg
    -0.64
    POSITIVE LOGITS
     Lumpur
    1.04
     Aires
    1.03
     Dame
    1.03
     Hills
    0.97
    burgh
    0.84
     Peninsula
    0.83
     Kong
    0.76
    minster
    0.75
     peninsula
    0.74
    brook
    0.73
    Act Density 0.050%

    No Known Activations