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

    Neuronpedia

    INDEX
    Explanations

    URLs and website-related terms

    oai_token-act-pair · gpt-3.5-turbo

    numeric values or references to URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frontline
    -0.71
     silenced
    -0.67
     spitting
    -0.65
     encomp
    -0.65
    etheless
    -0.64
     orchestr
    -0.64
     marching
    -0.64
     axe
    -0.63
     triggered
    -0.62
     union
    -0.61
    POSITIVE LOGITS
    Advertisement
    1.55
    RAW
    1.24
    advertisement
    1.23
    Newsletter
    1.17
    Advertisements
    1.17
    Another
    1.12
    Article
    1.12
    Spons
    1.11
    About
    1.11
    More
    1.10
    Act Density 0.786%

    No Known Activations