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

    Neuronpedia

    INDEX
    Explanations

    file extensions (e.g., HTML, PDF) within text

    oai_token-act-pair · gpt-3.5-turbo

    file formats and document types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strugg
    -0.79
     endeav
    -0.70
    iliated
    -0.68
    omnia
    -0.68
     exha
    -0.68
     neighb
    -0.67
    independence
    -0.67
    iann
    -0.66
    athered
    -0.64
     periodic
    -0.64
    POSITIVE LOGITS
     Quote
    1.35
     Accessed
    1.28
     âĨij
    1.25
     http
    1.25
     https
    1.20
     Retrieved
    1.18
    <|endoftext|>
    1.16
     Anyway
    1.14
     Apparently
    1.11
     Interestingly
    1.11
    Act Density 0.253%

    No Known Activations