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

    Neuronpedia

    INDEX
    Explanations

    terms related to diplomacy and diplomatic actions

    oai_token-act-pair · gpt-3.5-turbo

    references to diplomatic interactions and relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.81
    gger
    -0.78
    runs
    -0.75
    isode
    -0.74
    omething
    -0.71
    hra
    -0.71
    oven
    -0.71
    stadt
    -0.69
    fall
    -0.68
    pend
    -0.67
    POSITIVE LOGITS
     diplomatic
    1.03
     diplomacy
    0.95
     embassy
    0.90
     correctness
    0.88
     corps
    0.87
     relations
    0.84
     cables
    0.84
     immunity
    0.84
     espionage
    0.83
     reception
    0.82
    Act Density 0.011%

    No Known Activations