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

    Neuronpedia

    INDEX
    Explanations

    words related to policies and regulations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     scrib
    -0.70
     pope
    -0.70
     astronomer
    -0.68
     handwriting
    -0.68
     proverb
    -0.68
     illiter
    -0.67
     poet
    -0.66
     biologist
    -0.65
     resemblance
    -0.65
    aphael
    -0.65
    POSITIVE LOGITS
     systems
    0.94
     buildings
    0.93
     premises
    0.93
     products
    0.93
     enterprises
    0.92
     subsidiaries
    0.90
     establishments
    0.90
     campuses
    0.89
     facilities
    0.89
     workplaces
    0.88
    Act Density 0.971%

    No Known Activations