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

    Neuronpedia

    INDEX
    Explanations

    mentions of political or governmental institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government and its various roles and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tome
    -0.79
     Carnival
    -0.76
    hirt
    -0.75
     Width
    -0.70
    east
    -0.69
    ammers
    -0.68
    onge
    -0.67
     Wand
    -0.66
    terday
    -0.66
    CONT
    -0.66
    POSITIVE LOGITS
     shutdown
    1.13
     Accountability
    1.10
     agencies
    1.09
     bureaucracy
    0.96
     watchdog
    0.92
     officials
    0.92
     oversight
    0.91
     subsidized
    0.89
     accountability
    0.87
     funded
    0.87
    Act Density 0.073%

    No Known Activations