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

    Neuronpedia

    INDEX
    Explanations

    references to valuable or precious items, particularly treasure

    oai_token-act-pair · gpt-3.5-turbo

    references to treasures, wealth, and valuable items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osuke
    -0.72
    okin
    -0.72
    enegger
    -0.69
    SPA
    -0.69
    ells
    -0.69
    arel
    -0.67
    aren
    -0.67
    sen
    -0.66
    kins
    -0.66
    appa
    -0.65
    POSITIVE LOGITS
     trove
    1.44
     chests
    0.91
     treasure
    0.84
    collection
    0.84
     treasures
    0.84
     riches
    0.82
     Treasure
    0.81
    asures
    0.81
    asure
    0.79
     hoard
    0.78
    Act Density 0.019%

    No Known Activations