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

    Neuronpedia

    INDEX
    Explanations

    information related to academic studies, research findings, and analytical reports

    oai_token-act-pair · gpt-3.5-turbo

    references to research studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.59
    cffffcc
    -0.58
    bley
    -0.46
    toe
    -0.43
    !).
    -0.43
     remembers
    -0.43
    kefeller
    -0.43
     sings
    -0.41
    UTERS
    -0.41
    tch
    -0.41
    POSITIVE LOGITS
     Agenda
    0.47
     Fitz
    0.43
     attribution
    0.43
     outcome
    0.42
     Princ
    0.41
    eteenth
    0.41
    folios
    0.40
     investig
    0.40
     finances
    0.40
     horizon
    0.39
    Act Density 2.232%

    No Known Activations