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

    Neuronpedia

    INDEX
    Explanations

    mentions of refugees

    oai_token-act-pair · gpt-3.5-turbo

    references to refugees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efer
    -0.80
    ATA
    -0.76
     snipp
    -0.74
    à¸
    -0.68
    ISTORY
    -0.68
    YES
    -0.67
    Sensor
    -0.67
    xy
    -0.67
    Owner
    -0.66
    cor
    -0.66
    POSITIVE LOGITS
     refugees
    1.53
     Refugees
    1.49
     refugee
    1.21
     orphans
    1.16
     Refugee
    1.13
     resettlement
    1.08
     asylum
    1.06
     fleeing
    1.04
     migrants
    0.94
     seekers
    0.88
    Act Density 0.010%

    No Known Activations