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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political activities and implications

    oai_token-act-pair · gpt-3.5-turbo

    references to political activities and security threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hatt
    -0.80
     padd
    -0.73
    BIP
    -0.72
     Bottle
    -0.72
     Canaver
    -0.72
     paddle
    -0.70
     Oaks
    -0.69
     McA
    -0.68
     Winchester
    -0.68
     Alloy
    -0.68
    POSITIVE LOGITS
     espionage
    1.39
     terrorist
    1.30
    ionage
    1.30
     embassies
    1.25
     foreign
    1.23
     geopolitical
    1.22
     adversaries
    1.22
     diplomatic
    1.19
     abroad
    1.19
     terrorism
    1.18
    Act Density 0.509%

    No Known Activations