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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "foreign"

    oai_token-act-pair · gpt-3.5-turbo

    references to foreign entities or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illation
    -0.79
    phasis
    -0.79
    displayText
    -0.77
    veyard
    -0.76
     DRAG
    -0.72
     Annotations
    -0.72
    APH
    -0.71
    ItemTracker
    -0.71
    DIT
    -0.71
    legraph
    -0.70
    POSITIVE LOGITS
     nationals
    1.06
     affairs
    0.97
     foreign
    0.90
     abroad
    0.86
     embassy
    0.81
     embassies
    0.80
     interference
    0.79
     overseas
    0.76
    policy
    0.75
     Affairs
    0.75
    Act Density 0.012%

    No Known Activations