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

    Neuronpedia

    INDEX
    Explanations

    informative snippets or excerpts from longer pieces of text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce lists or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -0.90
    alties
    -0.86
    ©¶æ¥µ
    -0.81
    xit
    -0.77
    ¨
    -0.73
    ãĥĺ
    -0.70
    culosis
    -0.70
    aith
    -0.70
    aeda
    -0.69
     Parenthood
    -0.69
    POSITIVE LOGITS
     excerpt
    0.88
     overview
    0.86
     preliminary
    0.83
     tentative
    0.81
     partial
    0.80
     provisional
    0.79
     link
    0.77
     rundown
    0.77
     illustration
    0.77
     handy
    0.77
    Act Density 0.123%

    No Known Activations