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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    names of U.S. states and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibus
    -0.71
    lihood
    -0.69
    veyard
    -0.69
    herer
    -0.69
    ĸļ
    -0.64
    ularity
    -0.64
    reviewed
    -0.63
    avez
    -0.62
    mble
    -0.61
    afort
    -0.61
    POSITIVE LOGITS
    ans
    0.88
     taxpayers
    0.87
     residents
    0.87
    's
    0.83
     officials
    0.83
     voters
    0.81
    ians
    0.81
     lawmakers
    0.76
     policymakers
    0.76
     citizens
    0.74
    Act Density 0.367%

    No Known Activations