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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics or different uses of the word "power"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to power dynamics and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.68
    apest
    -0.67
     Nationwide
    -0.67
    Ĭ±
    -0.65
    traumatic
    -0.65
    alus
    -0.64
    infeld
    -0.64
    lish
    -0.64
    hospital
    -0.64
    cised
    -0.63
    POSITIVE LOGITS
     amplification
    0.89
     ignition
    0.85
    achev
    0.81
     acceleration
    0.77
    ierrez
    0.75
     levers
    0.75
     ampl
    0.74
     amps
    0.74
     amplifier
    0.73
     propulsion
    0.73
    Act Density 0.304%

    No Known Activations