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

    Neuronpedia

    INDEX
    Explanations

    mentions of construction or building projects, especially related to infrastructure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     pse
    -0.76
    verbal
    -0.75
    nikov
    -0.73
     pim
    -0.72
    wcsstore
    -0.72
     congratulations
    -0.70
     congrat
    -0.69
    Reviewer
    -0.68
    xual
    -0.66
    vation
    -0.65
    POSITIVE LOGITS
     wetlands
    1.13
     Lake
    1.03
     southwest
    1.02
     farmland
    1.02
     southwestern
    1.00
     waterways
    0.99
     northeast
    0.98
     northern
    0.98
     northwest
    0.97
     northeastern
    0.96
    Act Density 0.286%

    No Known Activations