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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government agencies, policies, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    government agencies and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clair
    -0.90
    jin
    -0.84
    cham
    -0.80
    mates
    -0.79
    milo
    -0.78
    olson
    -0.77
    flows
    -0.77
    idious
    -0.77
    cloth
    -0.76
    gow
    -0.75
    POSITIVE LOGITS
     Commission
    1.06
     Bureau
    1.05
     Agency
    1.03
     Association
    0.99
     Administration
    0.99
     Foundation
    0.97
     Board
    0.97
     Accountability
    0.95
     Institute
    0.95
     Organization
    0.94
    Act Density 0.155%

    No Known Activations