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

    Neuronpedia

    INDEX
    Explanations

    mentions of numbers related to casualties and demographics in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data related to casualties and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Practices
    -0.71
    ogie
    -0.65
    cdn
    -0.64
     differs
    -0.62
     fits
    -0.62
    ciation
    -0.61
     Mahjong
    -0.61
     solves
    -0.61
    bara
    -0.60
     resembles
    -0.59
    POSITIVE LOGITS
     ones
    0.75
    rowing
    0.63
    )</
    0.63
    aband
    0.61
    enegger
    0.61
    apo
    0.60
     mention
    0.59
    otally
    0.58
    !).
    0.58
     aforementioned
    0.56
    Act Density 0.373%

    No Known Activations