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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific types of buildings, particularly churches

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     unit
    -0.84
     incident
    -0.75
     piece
    -0.74
     staffer
    -0.73
     team
    -0.72
     device
    -0.70
     crew
    -0.69
     captain
    -0.69
     affair
    -0.69
     project
    -0.68
    POSITIVE LOGITS
     churches
    2.30
     mosques
    2.19
     museums
    2.18
     airports
    2.13
     malls
    2.12
     stadiums
    2.04
     colleges
    2.00
     hotels
    1.99
     universities
    1.98
     hospitals
    1.96
    Act Density 0.082%

    No Known Activations