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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or relationships

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vasive
    -0.74
     firsthand
    -0.69
     cybersecurity
    -0.69
     trailers
    -0.69
    Privacy
    -0.68
     distractions
    -0.68
    ritz
    -0.67
     intrusive
    -0.67
    advertisement
    -0.67
    enture
    -0.65
    POSITIVE LOGITS
     TOTAL
    1.13
     $$
    1.11
    Assuming
    1.10
     Assuming
    1.09
     multiply
    1.05
     approx
    1.04
     averaged
    1.04
     totals
    1.03
     multiplied
    1.03
    total
    1.03
    Act Density 0.584%

    No Known Activations