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

    Neuronpedia

    INDEX
    Explanations

    proper nouns representing locations, particularly those with the suffix "-ville"

    oai_token-act-pair · gpt-3.5-turbo

    the specific word "ville" in various context related to towns or cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artisan
    -0.78
    Wan
    -0.77
    udic
    -0.75
    externalActionCode
    -0.74
    ighth
    -0.73
    efully
    -0.72
    articles
    -0.72
    ylan
    -0.72
    eared
    -0.71
    ittal
    -0.68
    POSITIVE LOGITS
    ville
    0.93
     Pike
    0.86
     Correctional
    0.79
     Parish
    0.79
     Ferry
    0.78
     Heights
    0.78
     Bapt
    0.77
     Courier
    0.75
     Gas
    0.73
     Royale
    0.72
    Act Density 0.017%

    No Known Activations