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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imates
    -0.73
    clud
    -0.67
     Vera
    -0.66
    actory
    -0.66
    untary
    -0.63
     Ratio
    -0.62
     Warrant
    -0.61
     Omni
    -0.61
    uran
    -0.61
     Cancel
    -0.60
    POSITIVE LOGITS
     correctness
    1.09
    clinton
    0.93
    eering
    0.92
    manship
    0.88
    hip
    0.83
    chool
    0.82
    hare
    0.81
    politics
    0.79
    atism
    0.78
     esp
    0.75
    Act Density 0.063%

    No Known Activations