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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to Russian government and military officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canterbury
    -0.91
     Tasman
    -0.91
     Hawkins
    -0.88
     Hancock
    -0.85
     Oaks
    -0.82
     Cricket
    -0.81
     Hawai
    -0.80
    Haw
    -0.77
     Hawaiian
    -0.76
     Auckland
    -0.75
    POSITIVE LOGITS
     Kremlin
    1.70
    к
    1.64
     Dmitry
    1.62
    Moscow
    1.60
     Vladimir
    1.59
     Putin
    1.59
     Moscow
    1.58
     Ð
    1.54
    Ð
    1.53
     Dmit
    1.52
    Act Density 0.527%

    No Known Activations