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

    Neuronpedia

    INDEX
    Explanations

    mentions of the government

    oai_token-act-pair · gpt-3.5-turbo

    references to government and its role in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tome
    -0.79
    CONT
    -0.74
    hirt
    -0.71
     Carnival
    -0.71
    sbm
    -0.70
    onge
    -0.68
    ammers
    -0.68
    tom
    -0.66
    amaz
    -0.66
    hots
    -0.66
    POSITIVE LOGITS
     shutdown
    1.16
     Accountability
    1.12
     agencies
    1.06
     bureaucracy
    0.99
     watchdog
    0.89
    wide
    0.87
     agency
    0.87
     officials
    0.86
     accountability
    0.85
     contractor
    0.85
    Act Density 0.066%

    No Known Activations