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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and identifiers in the context of documents or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.71
     onBackPressed
    -0.54
    tagHelperRunner
    -0.50
     Wright
    -0.50
     Humphries
    -0.48
    InputBorder
    -0.47
     nearly
    -0.46
     el
    -0.46
     bParam
    -0.45
    leetcode
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.77
     }}"></
    0.67
    󠁢
    0.65
     leſs
    0.63
     ſtill
    0.61
     purpoſe
    0.60
     habet
    0.60
    CWE
    0.59
     unſ
    0.59
     Perſ
    0.57
    Act Density 0.399%

    No Known Activations