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

    Neuronpedia

    INDEX
    Explanations

    phrases that assert affirmation or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.78
    webElementXpaths
    -0.77
     cherchés
    -0.69
    发表于
    -0.69
     LoggerFactory
    -0.66
     Quij
    -0.65
    :\/\/
    -0.64
    Rüyada
    -0.63
    LLocation
    -0.62
     Sopho
    -0.62
    POSITIVE LOGITS
     indeed
    2.33
    indeed
    1.97
     Indeed
    1.89
    Indeed
    1.84
     effectivement
    1.25
     inderdaad
    1.22
     efectivamente
    1.10
    确实
    0.98
    的确
    0.92
     memang
    0.90
    Act Density 0.173%

    No Known Activations