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

    Neuronpedia

    INDEX
    Explanations

    sections or markers related to experimental procedures and methodologies in scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    section headings and numbering in academic or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    section headers and subsection titles in academic and technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    correctly
    -0.44
     everytime
    -0.44
    せっかく
    -0.44
     viszont
    -0.43
    yarnpkg
    -0.40
     juuri
    -0.40
     tất
    -0.40
    every
    -0.40
     every
    -0.39
    whatever
    -0.39
    POSITIVE LOGITS
     description
    0.75
     overview
    0.74
     limitations
    0.71
     summary
    0.69
     characteristics
    0.67
     Overview
    0.66
     discussion
    0.64
     Summary
    0.63
     identification
    0.63
     considerations
    0.62
    Act Density 0.648%

    No Known Activations