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

    Neuronpedia

    INDEX
    Explanations

    word patterns related to specific scientific and technical jargon, particularly in the context of algorithms and computational processes

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

    algorithm or code-related identifiers and references in technical/scientific documents.

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

    algorithm and equation reference labels in academic papers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    nya
    -0.59
    n
    -0.52
    ness
    -0.52
    rock
    -0.51
    ring
    -0.51
    ss
    -0.50
    nin
    -0.49
    rus
    -0.49
    rings
    -0.49
    root
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.62
    eeeee
    0.55
    eeeeee
    0.51
     InputDecoration
    0.51
     Wiktionnaire
    0.49
    PreAuthorize
    0.49
    eeee
    0.49
    __(/*!
    0.48
    ChildScrollView
    0.46
     ModelExpression
    0.46
    Act Density 0.508%

    No Known Activations