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

    Neuronpedia

    INDEX
    Explanations

    indications of understanding or comprehension in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.73
    BorderFactory
    -0.62
    tanleria
    -0.61
    zarchiwizowane
    -0.57
    StoryboardSegue
    -0.54
    ThemeOverlay
    -0.51
    twimg
    -0.51
    chaik
    -0.50
    WriteBarrier
    -0.50
    κό
    -0.50
    POSITIVE LOGITS
     how
    4.56
    how
    3.31
    How
    2.73
     How
    2.71
     cómo
    2.57
     HOW
    2.47
     bagaimana
    2.41
    HOW
    2.41
     hvordan
    2.33
     miten
    2.03
    Act Density 1.131%

    No Known Activations