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

    Neuronpedia

    INDEX
    Explanations

    patterns that signal the beginning of a section or logical argument structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.62
    complexContent
    -0.60
    nloa
    -0.60
     Roskov
    -0.59
    geslacht
    -0.58
    SpringBoot
    -0.56
    webElementXpaths
    -0.55
    LookAnd
    -0.55
    SharedDtor
    -0.54
     Eilish
    -0.54
    POSITIVE LOGITS
    igsaw
    0.72
     levy
    0.64
    cifix
    0.64
    存于互联网档案馆
    0.62
     оригіналу
    0.62
     كومونز
    0.61
    addContainerGap
    0.61
     shepherds
    0.59
    囗
    0.58
     Yarm
    0.58
    Act Density 0.011%

    No Known Activations