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

    Neuronpedia

    INDEX
    Explanations

    socio-political terms related to power dynamics and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of dominance or dominant forces in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterdam
    -0.77
    hire
    -0.77
    dump
    -0.72
    neys
    -0.72
    adra
    -0.71
    abre
    -0.70
    adr
    -0.68
    chery
    -0.68
    ander
    -0.68
    roma
    -0.68
    POSITIVE LOGITS
     theme
    0.81
     themes
    0.72
     dominant
    0.72
     tendency
    0.72
     impression
    0.71
     role
    0.70
     personality
    0.70
     bidder
    0.68
     majority
    0.67
     male
    0.67
    Act Density 0.035%

    No Known Activations