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

    Neuronpedia

    INDEX
    Explanations

    locations or place names, especially towns

    oai_token-act-pair · gpt-3.5-turbo

    place names, specifically those ending in "town" or "ville."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vana
    -0.69
    ploma
    -0.67
     undermin
    -0.66
    wcsstore
    -0.66
     Lank
    -0.66
    ciplinary
    -0.66
    ONS
    -0.65
    isman
    -0.64
    adena
    -0.63
    emonic
    -0.63
    POSITIVE LOGITS
     Heights
    0.97
     Pike
    0.94
    sburgh
    0.94
    sburg
    0.92
     Township
    0.92
     Courier
    0.90
     Borough
    0.89
    shire
    0.88
    ships
    0.86
     Town
    0.84
    Act Density 0.082%

    No Known Activations