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

    Neuronpedia

    INDEX
    Explanations

    information related to statistical or numerical data

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rarity or infrequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     diseng
    -0.73
     Balance
    -0.71
     watered
    -0.67
     negotiating
    -0.66
    ļéĨĴ
    -0.66
    ayers
    -0.66
     subsidies
    -0.65
     mortg
    -0.65
     monet
    -0.64
     Pledge
    -0.63
    POSITIVE LOGITS
     rare
    1.32
     occurrence
    1.32
     rarity
    1.30
     uncommon
    1.23
     occurrences
    1.16
     sightings
    1.14
    usual
    1.12
     unusual
    1.12
    Uncommon
    1.11
    Rare
    1.10
    Act Density 0.590%

    No Known Activations