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

    Neuronpedia

    INDEX
    Explanations

    updates and corrections in text

    oai_token-act-pair · gpt-3.5-turbo

    updates and announcements in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Marginal
    -0.68
    oeuv
    -0.66
    soever
    -0.66
     outings
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    ãĤ´
    -0.62
     classmates
    -0.62
     nurture
    -0.61
    advant
    -0.61
    ²¾
    -0.60
    POSITIVE LOGITS
     typo
    1.20
     corrected
    1.05
     clarification
    1.02
     clarified
    1.00
     *)
    0.98
     .)
    0.97
    !]
    0.95
     commenters
    0.93
     commenter
    0.89
     deleted
    0.88
    Act Density 0.355%

    No Known Activations