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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the city of Delhi

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Delhi

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.83
    cies
    -0.75
     therapists
    -0.74
    NetMessage
    -0.72
    utic
    -0.69
    gey
    -0.69
    fam
    -0.68
    inelli
    -0.68
    hift
    -0.67
    xp
    -0.67
    POSITIVE LOGITS
     Pradesh
    0.96
    jriwal
    0.91
     Punjab
    0.75
    ennes
    0.75
    ascus
    0.74
     Delhi
    0.72
     Lumpur
    0.72
     Zoo
    0.70
    igans
    0.67
    scape
    0.67
    Act Density 0.019%

    No Known Activations