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

    Neuronpedia

    INDEX
    Explanations

    policy-related terms and political actions

    oai_token-act-pair · gpt-3.5-turbo

    references to social and economic policies affecting marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vant
    -0.64
    lor
    -0.62
    agonist
    -0.61
     Intent
    -0.60
    itely
    -0.58
     herein
    -0.58
    vous
    -0.57
    hid
    -0.57
    Feature
    -0.57
    fan
    -0.57
    POSITIVE LOGITS
     mosques
    1.06
     prisons
    1.00
     universities
    0.92
     Guantanamo
    0.91
     incarceration
    0.91
     hospitals
    0.90
     pensions
    0.89
     contraceptives
    0.89
     incarcer
    0.89
    TPP
    0.89
    Act Density 0.588%

    No Known Activations