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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to actions and statuses associated with people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asters
    -0.84
    aster
    -0.80
    Catalog
    -0.79
     arbitration
    -0.78
    consumer
    -0.78
     cas
    -0.76
    prim
    -0.76
    rawdownloadcloneembedreportprint
    -0.75
     commer
    -0.73
    aser
    -0.72
    POSITIVE LOGITS
     Hill
    2.60
    Hill
    2.55
    hill
    1.83
     hill
    1.79
     Hills
    1.50
     hills
    1.27
     Ridge
    1.19
     Fields
    1.19
     Swamp
    1.16
     Street
    1.09
    Act Density 0.155%

    No Known Activations