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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related keywords in programming or software contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    기
    -0.55
    세
    -0.55
    에
    -0.53
    중
    -0.52
    가
    -0.51
    조
    -0.51
    정
    -0.50
    점
    -0.49
    부
    -0.49
    대
    -0.49
    POSITIVE LOGITS
    NamedQueries
    0.41
     &___
    0.34
     ddelweddau
    0.33
    WriteBarrier
    0.32
    ictwo
    0.32
     Cumber
    0.32
     funnier
    0.31
     acompaña
    0.30
    AsUp
    0.29
    Yeet
    0.28
    Act Density 2.524%

    No Known Activations