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

    Neuronpedia

    INDEX
    Explanations

    words related to valuable artifacts or assets, particularly treasures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of treasure or valuables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okin
    -0.77
    osuke
    -0.72
    ells
    -0.69
    colo
    -0.68
    slow
    -0.67
    LINE
    -0.67
    SPA
    -0.66
    arel
    -0.65
    iop
    -0.65
    abad
    -0.64
    POSITIVE LOGITS
     trove
    1.43
     chests
    0.85
    collection
    0.84
     treasures
    0.83
     treasure
    0.83
     riches
    0.82
    asure
    0.81
    abilia
    0.79
    asures
    0.76
    vier
    0.75
    Act Density 0.019%

    No Known Activations