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

    Neuronpedia

    INDEX
    Explanations

    mentions of the United States

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     STATS
    -0.83
    ãĥ£
    -0.74
    */(
    -0.70
    bath
    -0.63
    dylib
    -0.62
    SHIP
    -0.62
    func
    -0.60
    merce
    -0.60
    blocks
    -0.59
     PIT
    -0.58
    POSITIVE LOGITS
    ierra
    0.81
    IX
    0.80
    oday
    0.78
    wan
    0.77
    ustain
    0.75
    ugg
    0.75
    outheast
    0.73
    gt
    0.72
    ADA
    0.72
    eed
    0.72
    Act Density 0.043%

    No Known Activations