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

    Neuronpedia

    INDEX
    Explanations

    locations, likely focusing on the city of Delhi

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location Delhi

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.94
    cies
    -0.88
    estern
    -0.72
    inelli
    -0.72
     Robertson
    -0.72
    utic
    -0.72
    htaking
    -0.72
    gey
    -0.70
     Hubbard
    -0.70
    xp
    -0.69
    POSITIVE LOGITS
     Pradesh
    0.95
    jriwal
    0.78
     Delhi
    0.76
     Punjab
    0.72
    ascus
    0.69
     ide
    0.69
    apolis
    0.67
     Lumpur
    0.67
    ennes
    0.66
     Railway
    0.65
    Act Density 0.016%

    No Known Activations