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

    Neuronpedia

    INDEX
    Explanations

    demographics based on age and gender

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic groups and their associated statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forcement
    -0.60
    Operation
    -0.60
    tainment
    -0.60
     triumph
    -0.58
     awaits
    -0.58
     havoc
    -0.58
     Guru
    -0.57
    apego
    -0.57
    eals
    -0.56
     sabotage
    -0.56
    POSITIVE LOGITS
     aged
    1.27
     surveyed
    1.17
     ages
    1.10
     who
    1.03
     polled
    1.03
    opausal
    0.97
     born
    0.93
     younger
    0.92
    living
    0.92
     residing
    0.91
    Act Density 0.194%

    No Known Activations