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

    Neuronpedia

    INDEX
    Explanations

    references to entities involved in conflict, suffering, or refugees

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     malpractice
    -0.91
     تضيفلها
    -0.69
     RemoteException
    -0.64
    </thead>
    -0.62
     IndexPath
    -0.61
    FTFY
    -0.60
     Picchu
    -0.60
    viewDidLoad
    -0.56
    amentals
    -0.56
    ื่อง
    -0.54
    POSITIVE LOGITS
     refugees
    1.72
     refugee
    1.66
     Refugees
    1.45
    refuge
    1.45
     Refugee
    1.43
    Refuge
    1.24
     réfugiés
    1.03
     Flücht
    0.94
     refugiados
    0.93
    acterial
    0.85
    Act Density 0.003%

    No Known Activations