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

    Neuronpedia

    INDEX
    Explanations

    town or city names

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places, specifically those ending in "ville."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     burdens
    -0.62
     linking
    -0.60
     emphasis
    -0.60
     neurot
    -0.59
     sealed
    -0.59
     Vaj
    -0.58
     seal
    -0.58
     Ivanka
    -0.58
     trillions
    -0.57
     stress
    -0.57
    POSITIVE LOGITS
    ville
    4.27
    VILLE
    2.79
    vill
    1.70
    vale
    1.57
    burg
    1.47
    boro
    1.44
    dale
    1.39
    bourg
    1.23
    burgh
    1.22
    erville
    1.22
    Act Density 0.022%

    No Known Activations