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

    Neuronpedia

    INDEX
    Explanations

    references to political roles and actions related to government and leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to female leadership roles, specifically in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [/
    -0.72
    ====
    -0.66
    quickShipAvailable
    -0.65
     Saying
    -0.64
     saying
    -0.63
    ================
    -0.63
     Falling
    -0.62
     Cancel
    -0.62
    Pause
    -0.61
     SAY
    -0.61
    POSITIVE LOGITS
     oversaw
    1.53
     helped
    1.39
     ensured
    1.27
     facilitated
    1.26
     aided
    1.26
     battled
    1.23
     guided
    1.23
     spearheaded
    1.23
     steered
    1.22
     interacted
    1.19
    Act Density 0.344%

    No Known Activations