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

    Neuronpedia

    INDEX
    Explanations

    phrases with repeated letters

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns, specifically those ending with the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     establishment
    -0.71
     Government
    -0.60
     Sawyer
    -0.58
     Economist
    -0.57
     Inquiry
    -0.57
     Establishment
    -0.56
     Let
    -0.55
     Gateway
    -0.55
     PATH
    -0.55
     Burma
    -0.54
    POSITIVE LOGITS
    ervatives
    1.11
    ilver
    1.10
    paces
    1.10
    hots
    1.10
    ynthesis
    1.09
    uits
    1.06
    peed
    1.06
    hips
    1.05
    isters
    1.05
    poons
    1.04
    Act Density 0.372%

    No Known Activations