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

    Neuronpedia

    INDEX
    Explanations

    mentions of nationalities or citizenship statuses

    oai_token-act-pair · gpt-3.5-turbo

    references to foreign nationals from various countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illery
    -0.67
     Ste
    -0.64
     Glass
    -0.61
    cape
    -0.61
     Armor
    -0.60
     Measure
    -0.59
    Bone
    -0.58
     Draper
    -0.57
    Ste
    -0.57
    thin
    -0.57
    POSITIVE LOGITS
     nationals
    3.84
     Nationals
    1.60
     foreigners
    1.37
     citizens
    1.35
     nationality
    1.30
    citizens
    1.21
     diplomats
    1.20
     embassies
    1.19
     citizenship
    1.13
     migrants
    1.12
    Act Density 0.008%

    No Known Activations