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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of 'exercising' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of exercising power or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pleted
    -0.75
    andro
    -0.71
     Cosponsors
    -0.70
     Dise
    -0.69
     Deaths
    -0.68
    dt
    -0.67
    azines
    -0.67
    bsite
    -0.64
     Alive
    -0.63
    opter
    -0.62
    POSITIVE LOGITS
     discretion
    1.19
     restraint
    1.19
     caution
    1.10
     utmost
    1.07
     undue
    1.03
     control
    0.98
     sovereignty
    0.97
     dominion
    0.97
     patience
    0.94
     influence
    0.94
    Act Density 0.094%

    No Known Activations