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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating individuality or personal agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.75
    ViewFeatures
    -0.65
    CppMethod
    -0.65
     "..\..\
    -0.64
     EconPapers
    -0.62
    uitable
    -0.61
    InstrumentedTest
    -0.60
    asteroide
    -0.60
    setupUi
    -0.57
     NDEBUG
    -0.57
    POSITIVE LOGITS
     alone
    1.21
     Alone
    1.03
    alone
    0.83
     itself
    0.82
     alleine
    0.81
     ALONE
    0.79
     alene
    0.79
     allein
    0.78
    Alone
    0.77
     sendiri
    0.76
    Act Density 0.185%

    No Known Activations