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

    Neuronpedia

    INDEX
    Explanations

    academic and research-related terms, such as "papers," "journal," and "citations."

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publications and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.67
    ALLY
    -0.62
    Spoiler
    -0.62
     Telegram
    -0.62
    ZI
    -0.60
     Flavoring
    -0.58
    arak
    -0.58
    URA
    -0.58
    sonian
    -0.56
     Dhabi
    -0.56
    POSITIVE LOGITS
    pread
    0.91
    matter
    0.84
     contained
    0.76
     priced
    0.74
    flows
    0.71
    afety
    0.71
     eaten
    0.71
     originated
    0.68
     sampled
    0.68
    ource
    0.67
    Act Density 0.519%

    No Known Activations