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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or connections between different entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "link."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parables
    -0.74
     Penguins
    -0.71
     Atmosp
    -0.70
     Nights
    -0.69
     diapers
    -0.67
     Predators
    -0.67
    perty
    -0.66
    ccording
    -0.66
     Pens
    -0.66
    ORK
    -0.65
    POSITIVE LOGITS
    link
    1.34
     link
    1.20
    edin
    1.19
     links
    1.13
    links
    1.09
    later
    1.08
     linking
    1.05
    linked
    0.84
    Link
    0.80
    chain
    0.79
    Act Density 0.014%

    No Known Activations