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

    Neuronpedia

    INDEX
    Explanations

    terms related to understanding or comprehension

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "understand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atel
    -0.71
    TION
    -0.67
    drop
    -0.67
    ħ
    -0.64
    ump
    -0.63
     Temporary
    -0.60
     Corpse
    -0.56
    cake
    -0.56
    cakes
    -0.56
     Newspaper
    -0.56
    POSITIVE LOGITS
     understand
    3.26
     understands
    2.17
     understanding
    2.09
     Understand
    2.03
     understood
    2.01
     comprehend
    1.91
     realize
    1.64
     grasp
    1.62
     appreciate
    1.60
     Understanding
    1.58
    Act Density 0.020%

    No Known Activations