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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals holding positions of authority or leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to leadership positions, specifically chairs of committees or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.91
     condu
    -0.63
     DATA
    -0.62
    ogue
    -0.61
    DEF
    -0.59
     rugged
    -0.59
     JUSTICE
    -0.59
    ILLE
    -0.59
     conver
    -0.59
     suscept
    -0.59
    POSITIVE LOGITS
    chair
    1.19
    person
    1.13
    woman
    1.13
     chair
    1.11
    manship
    1.08
    mans
    1.05
    lift
    1.04
    chairs
    1.02
    holder
    1.01
    pins
    0.97
    Act Density 0.016%

    No Known Activations