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

    Neuronpedia

    INDEX
    Explanations

    references to methods and properties in programming code, particularly involving method names and their associated default values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +'_
    -0.17
    å§
    -0.17
    +"_
    -0.16
    agrams
    -0.16
    startsWith
    -0.15
    .TestTools
    -0.14
    ==='
    -0.14
    aser
    -0.14
    =NULL
    -0.14
    .'_
    -0.13
    POSITIVE LOGITS
     Escape
    0.16
    ulp
    0.16
    æħĭ
    0.16
    aida
    0.15
     escaping
    0.15
    aid
    0.15
     +
    0.14
    orsi
    0.14
     Decoration
    0.14
    etus
    0.14
    Act Density 0.045%

    No Known Activations