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

    Neuronpedia

    INDEX
    Explanations

    references to North Korea

    oai_token-act-pair · gpt-3.5-turbo

    mentions of North Korea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llo
    -0.84
    gio
    -0.75
    byss
    -0.74
    Lens
    -0.71
    ++++++++++++++++
    -0.70
    gerald
    -0.69
    Compan
    -0.68
    pub
    -0.68
    vier
    -0.68
    ttes
    -0.67
    POSITIVE LOGITS
    orea
    1.12
     missile
    1.09
     missiles
    1.02
     Pyongyang
    0.99
     Jong
    0.91
     dictator
    0.88
     DPRK
    0.87
     ballistic
    0.86
     Koreans
    0.84
    ongyang
    0.84
    Act Density 0.046%

    No Known Activations