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

    Neuronpedia

    INDEX
    Explanations

    academic language related to research papers, particularly those that discuss frameworks and analyses in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wikipedia
    -0.16
    stroy
    -0.15
    ansson
    -0.14
    nergy
    -0.14
    uars
    -0.14
     Wikipedia
    -0.13
    oire
    -0.13
    &page
    -0.13
     compar
    -0.13
     Gus
    -0.13
    POSITIVE LOGITS
     novel
    0.20
    plet
    0.19
    æĸ°çļĦ
    0.18
    ovel
    0.18
     framework
    0.16
     unprecedented
    0.16
    ä¸Ģç§į
    0.16
    nov
    0.15
     Novel
    0.14
     approach
    0.14
    Act Density 0.109%

    No Known Activations