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

    Neuronpedia

    INDEX
    Explanations

    common words in the English language, without capturing a specific theme or pattern

    oai_token-act-pair · gpt-3.5-turbo

    references to quintiles in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tissues
    -0.68
     mamm
    -0.67
    Downloadha
    -0.64
    FORE
    -0.62
     tissue
    -0.60
     Victims
    -0.60
     Delivery
    -0.59
    ntil
    -0.58
    Interstitial
    -0.56
     lifting
    -0.56
    POSITIVE LOGITS
    essential
    1.10
    uple
    1.10
    ophon
    0.97
     Quint
    0.94
    ieth
    0.93
     quint
    0.90
    encies
    0.87
    ilant
    0.86
    illion
    0.86
    ivari
    0.85
    Act Density 0.008%

    No Known Activations