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

    Neuronpedia

    INDEX
    Explanations

    mentions of international relations and human rights

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to humanitarian or rights organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.70
     lockout
    -0.69
     ..........
    -0.68
    peat
    -0.68
     infringing
    -0.65
    mallow
    -0.64
    hematically
    -0.63
    iseum
    -0.62
    ativity
    -0.62
    conom
    -0.61
    POSITIVE LOGITS
     UNHCR
    1.39
     NGO
    1.26
     embassies
    1.25
     NGOs
    1.24
     embassy
    1.20
     humanitarian
    1.18
     diplomatic
    1.17
     diplomats
    1.11
     diplomacy
    1.10
     Kurd
    1.04
    Act Density 1.151%

    No Known Activations