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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or places, such as hometowns or cities

    oai_token-act-pair · gpt-3.5-turbo

    references to people's hometowns and related locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.80
    odiac
    -0.79
    Adapt
    -0.77
    ecycle
    -0.77
    inventoryQuantity
    -0.74
    ividual
    -0.74
    ensibly
    -0.73
     Featured
    -0.72
    cellaneous
    -0.72
    equal
    -0.69
    POSITIVE LOGITS
     Tanzania
    0.89
     Ethiopia
    0.83
     Latvia
    0.82
     Rochester
    0.82
     Judah
    0.79
     Argentina
    0.79
     Naples
    0.77
     Bosnia
    0.77
     Italy
    0.76
     Normandy
    0.75
    Act Density 0.131%

    No Known Activations