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

    Neuronpedia

    INDEX
    Explanations

    titles or positions related to leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in leadership positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.76
     tatt
    -0.73
     Adin
    -0.64
     Bagg
    -0.64
     detention
    -0.62
     Collider
    -0.61
     conclud
    -0.61
     tolerance
    -0.61
     suscept
    -0.61
     infringing
    -0.60
    POSITIVE LOGITS
    manship
    1.71
    woman
    1.68
    person
    1.51
    men
    1.38
    mans
    1.37
    women
    1.35
    lift
    1.30
    pers
    1.24
    man
    1.12
    boards
    1.06
    Act Density 0.024%

    No Known Activations