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

    Neuronpedia

    INDEX
    Explanations

    locations within a city

    oai_token-act-pair · gpt-3.5-turbo

    references to different sides of cities or neighborhoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omb
    -0.82
    thood
    -0.77
    AUT
    -0.75
    wcsstore
    -0.73
    ongyang
    -0.72
    poll
    -0.72
    gey
    -0.70
    ichick
    -0.70
    animate
    -0.69
    oming
    -0.68
    POSITIVE LOGITS
     Highway
    0.92
     Avenue
    0.91
     Plaza
    0.81
     Parkway
    0.78
     diner
    0.78
     Craigslist
    0.78
     Heights
    0.78
     motel
    0.76
     Hotel
    0.76
    stones
    0.76
    Act Density 0.025%

    No Known Activations