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

    Neuronpedia

    INDEX
    Explanations

    references to authors and authorship

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

    author or authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GridItem
    -0.39
     protocols
    -0.36
     Ergo
    -0.35
     obec
    -0.35
     Clever
    -0.34
     merav
    -0.33
    hote
    -0.32
     Equilibrium
    -0.32
     Protocols
    -0.32
     ligiloj
    -0.32
    POSITIVE LOGITS
     Author
    1.82
     Authors
    1.31
     AUTHOR
    1.16
    Author
    1.08
     Autor
    0.96
     author
    0.88
     作者
    0.84
     Автор
    0.81
     AUTOR
    0.78
    Autor
    0.78
    Act Density 0.003%

    No Known Activations