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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Lat"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Latina" and its various forms or mentions in contexts related to culture or political representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akura
    -0.79
    ilogy
    -0.77
    awaru
    -0.70
     Gandhi
    -0.70
    utra
    -0.69
    utsu
    -0.67
    rafted
    -0.65
    etsu
    -0.65
     overr
    -0.64
     overriding
    -0.64
    POSITIVE LOGITS
     Lat
    4.00
    Lat
    3.48
     lat
    2.33
    lat
    2.02
     LAT
    1.72
     Latvia
    1.71
     latitude
    1.38
     Latino
    1.33
    Latin
    1.33
     latency
    1.21
    Act Density 0.019%

    No Known Activations