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

    Neuronpedia

    INDEX
    Explanations

    words related to physical structures, particularly buildings

    oai_token-act-pair · gpt-3.5-turbo

    references to buildings and their condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nir
    -0.98
    CHAT
    -0.76
    vous
    -0.73
    sha
    -0.73
    ño
    -0.72
    tle
    -0.70
     Nadu
    -0.70
    owder
    -0.67
    sweet
    -0.65
    Consumer
    -0.64
    POSITIVE LOGITS
     buildings
    1.15
    raper
    1.06
     erected
    1.02
     Buildings
    0.99
     blocks
    0.96
     skysc
    0.94
     constructed
    0.87
    chool
    0.86
     dwellings
    0.84
     building
    0.83
    Act Density 0.029%

    No Known Activations