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

    Neuronpedia

    INDEX
    Explanations

    incorrectly stated facts that require correction

    oai_token-act-pair · gpt-3.5-turbo

    editorial notes and corrections in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.86
    å¥
    -0.73
    çļ
    -0.71
    cosystem
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.68
    utics
    -0.66
    ãĤ¤ãĥĪ
    -0.65
     srfAttach
    -0.65
    é£
    -0.64
    forts
    -0.63
    POSITIVE LOGITS
     *)
    1.02
     typo
    0.92
     deleted
    0.86
     incorrectly
    0.81
     formatting
    0.78
     .)
    0.77
     ONLY
    0.77
     DID
    0.77
     incorrect
    0.76
    !]
    0.75
    Act Density 0.553%

    No Known Activations