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

    Neuronpedia

    INDEX
    Explanations

    references to quotations and attribution in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.15
    ViewFeatures
    -0.85
    EndInit
    -0.77
     '\\;'
    -0.75
    SharedDtor
    -0.73
    ChildScrollView
    -0.72
    :✨
    -0.71
    setVerticalGroup
    -0.70
    AccessorTable
    -0.70
    aarrggbb
    -0.69
    POSITIVE LOGITS
    中略
    1.11
    sic
    0.98
     itſelf
    0.71
    ..]
    0.71
     pleaſure
    0.70
     purpoſe
    0.67
    ..)
    0.67
     beſt
    0.67
    ,]
    0.67
    ſelves
    0.64
    Act Density 0.133%

    No Known Activations