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

    Neuronpedia

    INDEX
    Explanations

    words related to contributions and containing elements or processes

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

    The neuron identifies the word "cont" and its variations (like "contributed" and "contrast") in scientific and technical documents.

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

    author contribution statements and attributions in academic papers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     avoient
    -0.63
    +#+#
    -0.60
    RegressionTest
    -0.59
    Traducción
    -0.58
     CreateTagHelper
    -0.57
     ainfi
    -0.57
    OGND
    -0.57
    期刊论文
    -0.54
     AssemblyTitle
    -0.54
    tagPool
    -0.52
    POSITIVE LOGITS
    Cont
    0.46
    antd
    0.46
     Cont
    0.45
     cont
    0.42
    cont
    0.42
     Conti
    0.39
    XMLSchema
    0.37
    Dorm
    0.37
     Kont
    0.37
     contin
    0.36
    Act Density 0.308%

    No Known Activations