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

    Neuronpedia

    INDEX
    Explanations

    references to political leaders or high-ranking officials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders and their relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Denver
    -1.11
     comet
    -0.91
     Weld
    -0.88
    Pokemon
    -0.88
     Comet
    -0.85
    stanbul
    -0.84
     Boulder
    -0.84
     Pokemon
    -0.84
    Magikarp
    -0.82
     Denver
    -0.82
    POSITIVE LOGITS
     Rwanda
    1.98
     Uganda
    1.93
     Congo
    1.91
     Rw
    1.81
     Zimbabwe
    1.81
     Tanzania
    1.69
     Ug
    1.65
     Africans
    1.64
     Zamb
    1.63
     Kenya
    1.63
    Act Density 0.488%

    No Known Activations