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

    Neuronpedia

    INDEX
    Explanations

    references to the use of people as resources and the importance of language in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llen
    -0.23
    breadcrumb
    -0.19
    едини
    -0.17
    ãĥ¼ãĥĭ
    -0.16
    isphere
    -0.15
     Wright
    -0.15
    rne
    -0.14
     Wilson
    -0.14
    Untitled
    -0.14
    erule
    -0.14
    POSITIVE LOGITS
     restart
    0.22
     Inch
    0.20
     todo
    0.20
     alist
    0.18
     Todo
    0.18
     livelihood
    0.17
     jel
    0.17
     resume
    0.17
    aida
    0.16
     caliber
    0.16
    Act Density 0.006%

    No Known Activations