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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comprehension and understanding of complex ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ônimo
    -0.61
    neiden
    -0.56
    お待ちしております
    -0.55
    AsUp
    -0.54
     дописавши
    -0.53
    ISLAM
    -0.52
    orianCalendar
    -0.52
     against
    -0.51
    ränken
    -0.51
     resourceCulture
    -0.51
    POSITIVE LOGITS
     understand
    1.04
    understand
    1.04
     Understand
    0.99
     understanding
    0.98
     entender
    0.97
     understood
    0.97
    Understand
    0.97
    understood
    0.97
     comprehension
    0.94
     understandings
    0.84
    Act Density 0.411%

    No Known Activations