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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government, politics, and legislative actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tome
    -0.81
    hirt
    -0.73
    terday
    -0.73
     Carnival
    -0.73
     Width
    -0.72
    east
    -0.72
    onge
    -0.69
    CONT
    -0.69
    ammers
    -0.68
    jen
    -0.67
    POSITIVE LOGITS
     agencies
    1.14
     shutdown
    1.07
     bureaucracy
    1.05
     Accountability
    1.04
     officials
    0.96
     institutions
    0.93
     oversight
    0.92
     intervention
    0.91
     subsidized
    0.91
     watchdog
    0.90
    Act Density 0.064%

    No Known Activations