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

    Neuronpedia

    INDEX
    Explanations

    locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    geographic or organizational names and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     similar
    -0.71
     warranty
    -0.68
     alt
    -0.64
     overw
    -0.64
     visible
    -0.62
     routine
    -0.62
     concealed
    -0.62
     masked
    -0.62
     prior
    -0.62
     worthwhile
    -0.61
    POSITIVE LOGITS
    assian
    1.13
    elia
    1.08
    leton
    1.08
    ley
    1.00
    ena
    1.00
    hani
    1.00
    ham
    0.98
    hart
    0.97
    ayne
    0.96
    ford
    0.96
    Act Density 0.187%

    No Known Activations