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

    Neuronpedia

    INDEX
    Explanations

    the start of a new section or paragraph in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.41
    HasKey
    -0.39
     has
    -0.39
    .
    -0.39
      
    -0.38
    분
    -0.38
     co
    -0.37
    ↵↵
    -0.36
    ↵
    -0.36
    :
    -0.35
    POSITIVE LOGITS
     disambiguazione
    1.14
     kasarigan
    1.06
     تانيه
    1.02
     ujednoznacz
    1.00
     المعيارى
    1.00
    yntaxException
    0.97
     виправивши
    0.94
    verwijspagina
    0.91
     للمعارف
    0.88
    onViewCreated
    0.88
    Act Density 0.002%

    No Known Activations