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

    Neuronpedia

    INDEX
    Explanations

    mentions of refugees and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to refugees and their situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cor
    -0.79
    æ©Ł
    -0.76
    efer
    -0.73
    alyses
    -0.71
    tests
    -0.70
    verages
    -0.70
    à¸
    -0.70
    OPA
    -0.69
    adden
    -0.69
    phalt
    -0.68
    POSITIVE LOGITS
     refugees
    1.31
     Refugees
    1.28
     resettlement
    1.25
     fleeing
    1.20
     refugee
    1.15
     Refugee
    1.07
     UNHCR
    1.05
     asylum
    1.03
     shelter
    0.89
     camps
    0.88
    Act Density 0.036%

    No Known Activations