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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deep understanding or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onies
    -0.81
    quer
    -0.72
    inating
    -0.70
    photos
    -0.67
    yss
    -0.65
     chopping
    -0.65
    strip
    -0.64
    cake
    -0.62
    cow
    -0.62
    join
    -0.61
    POSITIVE LOGITS
     Understanding
    0.88
     comprehension
    0.84
     understanding
    0.84
    FUL
    0.79
     OF
    0.78
     Understand
    0.76
     thereof
    0.76
    ably
    0.74
    ledge
    0.72
    ually
    0.72
    Act Density 0.021%

    No Known Activations