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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly focusing on men

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Supplement
    -0.71
     Pact
    -0.62
     Liberties
    -0.62
     practice
    -0.60
     precaution
    -0.60
     remembrance
    -0.59
     Skyrim
    -0.59
     mutual
    -0.58
     Destination
    -0.58
    terday
    -0.58
    POSITIVE LOGITS
    osphere
    1.12
    liest
    1.09
    uscript
    1.07
     responsible
    0.98
    hunt
    0.96
    abase
    0.90
    WithNo
    0.88
    iest
    0.88
    responsible
    0.85
    onymous
    0.81
    Act Density 0.096%

    No Known Activations