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

    Neuronpedia

    INDEX
    Explanations

    references to refugees and refugee-related situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of refugees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cor
    -0.81
    æ©Ł
    -0.76
    OPA
    -0.76
    efer
    -0.72
    à¸
    -0.70
    ISION
    -0.70
    tests
    -0.69
    phalt
    -0.69
    ritic
    -0.69
    reme
    -0.68
    POSITIVE LOGITS
     resettlement
    1.28
     refugees
    1.25
     Refugees
    1.22
     fleeing
    1.19
     refugee
    1.15
     Refugee
    1.05
     UNHCR
    1.04
     camps
    1.02
     asylum
    0.95
     shelters
    0.90
    Act Density 0.041%

    No Known Activations