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

    Neuronpedia

    INDEX
    Explanations

    adverbs before a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "barely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WER
    -0.71
    Reviewer
    -0.69
     Origins
    -0.67
    ItemThumbnailImage
    -0.64
     Sequence
    -0.64
     Values
    -0.64
     Types
    -0.64
    ãĥ¤
    -0.62
    idon
    -0.61
    sequence
    -0.60
    POSITIVE LOGITS
    icable
    0.85
    WARE
    0.79
     survived
    0.78
     escaped
    0.75
     percept
    0.74
     graz
    0.74
    doms
    0.74
     scraping
    0.73
    Ń·
    0.73
     surviving
    0.72
    Act Density 0.008%

    No Known Activations