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

    Neuronpedia

    INDEX
    Explanations

    references to political and social critiques related to power dynamics and inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ministers
    -0.15
    qq
    -0.15
    orde
    -0.14
    ronic
    -0.14
    Å¡et
    -0.14
    OLS
    -0.14
    lef
    -0.14
    uk
    -0.13
    wide
    -0.13
    abee
    -0.13
    POSITIVE LOGITS
     United
    0.21
     scales
    0.18
     country
    0.18
     Koch
    0.17
     Bible
    0.17
     House
    0.17
     White
    0.16
     Found
    0.16
     current
    0.16
     fram
    0.16
    Act Density 0.590%

    No Known Activations