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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional or subjective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    When
    -0.50
     When
    -0.47
     sonra
    -0.46
     kemudian
    -0.45
    それを
    -0.44
    when
    -0.43
     őket
    -0.43
     cuando
    -0.43
     quando
    -0.42
     потім
    -0.42
    POSITIVE LOGITS
     there
    0.94
     indeed
    0.91
    SharedCtor
    0.88
     '{@
    0.87
    Према
    0.84
    这是一
    0.83
    indeed
    0.80
     handelt
    0.80
    contentLoaded
    0.79
    AddTagHelper
    0.79
    Act Density 0.416%

    No Known Activations