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

    Neuronpedia

    INDEX
    Explanations

    various expressions and contexts related to power

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "power" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALK
    -0.71
     Yad
    -0.70
     Settlement
    -0.70
     Sett
    -0.66
     Colony
    -0.65
    romeda
    -0.65
    akeru
    -0.65
    ajor
    -0.65
    vironment
    -0.64
     Kern
    -0.64
    POSITIVE LOGITS
    stroke
    0.97
     cords
    0.86
    full
    0.86
    houses
    0.86
    lessness
    0.83
    lifting
    0.82
     chords
    0.81
    bang
    0.80
    ups
    0.80
     surge
    0.80
    Act Density 0.059%

    No Known Activations