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

    Neuronpedia

    INDEX
    Explanations

    mentions of government entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government actions and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rank
    -0.72
    sbm
    -0.71
     Nig
    -0.69
     Junction
    -0.69
     Locations
    -0.68
     Heaven
    -0.67
    COMPLE
    -0.66
     Plate
    -0.66
    colo
    -0.66
    outh
    -0.66
    POSITIVE LOGITS
     Accountability
    0.93
     bureaucracy
    0.91
     agencies
    0.90
     watchdog
    0.88
     subsidized
    0.87
     shutdown
    0.85
    's
    0.83
     subsidy
    0.82
     coffers
    0.81
     planners
    0.81
    Act Density 0.081%

    No Known Activations