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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or scenarios that begin with "When"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.58
     للمعارف
    -0.50
    帖最后由
    -0.48
    WriteTagHelper
    -0.47
    出版年
    -0.43
    ----</
    -0.43
     further
    -0.41
     jScrollPane
    -0.41
    Eu
    -0.40
     CreateTagHelper
    -0.40
    POSITIVE LOGITS
     when
    0.89
     When
    0.85
     quando
    0.85
     Cuando
    0.85
     cuando
    0.85
    when
    0.85
    When
    0.82
     når
    0.80
     когда
    0.79
    cuando
    0.79
    Act Density 0.591%

    No Known Activations