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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their affiliations or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     z
    -0.40
    โย
    -0.39
     too
    -0.38
     jong
    -0.38
     I
    -0.37
     ever
    -0.37
     good
    -0.36
     just
    -0.36
     Good
    -0.36
     DO
    -0.35
    POSITIVE LOGITS
     Administrativna
    0.79
     AssemblyCompany
    0.75
    تقاوى
    0.68
    Ӕ
    0.65
     betweenstory
    0.62
    EndContext
    0.62
    RenderAtEndOf
    0.61
    PerformLayout
    0.61
    Parcelize
    0.61
     समीक्षाओं
    0.60
    Act Density 0.635%

    No Known Activations