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

    Neuronpedia

    INDEX
    Explanations

    words related to construction, particularly buildings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of buildings and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nir
    -0.99
    CHAT
    -0.81
    geon
    -0.69
    sweet
    -0.69
    sha
    -0.68
    vous
    -0.67
    Consumer
    -0.66
    DOS
    -0.65
     Sturgeon
    -0.65
    dos
    -0.64
    POSITIVE LOGITS
     buildings
    1.12
     erected
    1.07
    raper
    1.03
     Buildings
    0.96
     skysc
    0.93
    hips
    0.91
     constructed
    0.87
     blocks
    0.87
    chool
    0.85
     crumble
    0.84
    Act Density 0.057%

    No Known Activations