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

    Neuronpedia

    INDEX
    Explanations

    words related to legislation and governance

    oai_token-act-pair · gpt-3.5-turbo

    instances of statistical or numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     que
    -0.71
     unidentified
    -0.70
     swe
    -0.68
     Saiyan
    -0.65
     undet
    -0.64
     scripted
    -0.64
     bundled
    -0.64
     spitting
    -0.63
     triggered
    -0.63
     commission
    -0.62
    POSITIVE LOGITS
    Advertisement
    1.64
    Conclusion
    1.57
    Finally
    1.56
    Lastly
    1.54
    Another
    1.53
    Similarly
    1.51
    Furthermore
    1.51
    advertisement
    1.48
    Anyway
    1.47
    CONCLUS
    1.47
    Act Density 0.542%

    No Known Activations