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

    Neuronpedia

    INDEX
    Explanations

    specific city names, especially related to India

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly those related to locations and cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Staten
    -0.80
    ages
    -0.78
    RH
    -0.75
    ifts
    -0.71
    Atlantic
    -0.70
     Goodell
    -0.70
    innacle
    -0.69
    Weiss
    -0.68
    Newsletter
    -0.65
     Kessler
    -0.65
    POSITIVE LOGITS
     Pradesh
    1.36
     Sharma
    1.23
    umbai
    1.12
    jriwal
    1.12
     Singh
    1.05
     Sabha
    1.01
     crore
    1.01
     Nadu
    1.00
     Bhar
    0.96
     Patel
    0.94
    Act Density 0.076%

    No Known Activations