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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political conflict and governmental actions

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "government" within a political or conflict context

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    CONT
    -0.94
    orem
    -0.68
     Roses
    -0.67
    sbm
    -0.67
    ostic
    -0.67
     Rider
    -0.67
    vae
    -0.66
    Lens
    -0.65
    Ward
    -0.65
     Locations
    -0.65
    POSITIVE LOGITS
     bureaucracy
    1.02
     officials
    0.96
     agencies
    0.95
     administration
    0.94
     government
    0.94
     shutdown
    0.91
     administrator
    0.90
     authorities
    0.87
     agency
    0.85
     decree
    0.84
    Act Density 0.058%

    No Known Activations