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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of exerting power or authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of exercising power or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opter
    -0.73
    pleted
    -0.72
    apest
    -0.72
    opsis
    -0.69
    soon
    -0.67
     Cosponsors
    -0.67
     attm
    -0.66
    ney
    -0.64
    stration
    -0.63
    opers
    -0.62
    POSITIVE LOGITS
     discretion
    1.33
     restraint
    1.13
     autonomy
    1.13
     caution
    1.09
     authority
    1.08
     dominion
    1.07
     utmost
    1.07
     control
    1.06
     jurisdiction
    1.05
     sovereignty
    1.03
    Act Density 0.087%

    No Known Activations