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

    Neuronpedia

    INDEX
    Explanations

    phrases related to buildings and their characteristics, especially focusing on the number of stories

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of stories in buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uncture
    -0.88
    oglobin
    -0.73
    wana
    -0.72
    gotten
    -0.71
    anson
    -0.70
    Money
    -0.69
    ubric
    -0.69
    ibaba
    -0.67
     Nieto
    -0.67
     Canaver
    -0.66
    POSITIVE LOGITS
     apartment
    1.12
     buildings
    1.11
     balcony
    1.11
     apartments
    1.07
     tower
    1.04
     towers
    1.04
     residential
    0.96
     occupancy
    0.95
     dwellings
    0.92
     skysc
    0.90
    Act Density 0.087%

    No Known Activations