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

    Neuronpedia

    INDEX
    Explanations

    words related to political control and power

    oai_token-act-pair · gpt-3.5-turbo

    references to political control and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idered
    -0.68
    Recommend
    -0.67
     Tale
    -0.67
    asca
    -0.60
     Adventures
    -0.59
    uni
    -0.59
    pheus
    -0.59
    enegger
    -0.58
     Honour
    -0.58
    rehend
    -0.57
    POSITIVE LOGITS
    eering
    0.89
    orship
    0.89
    ership
    0.85
     control
    0.82
    lessness
    0.79
    taker
    0.78
    ignty
    0.77
    ANCE
    0.77
    iveness
    0.77
     levers
    0.75
    Act Density 0.054%

    No Known Activations