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

    Neuronpedia

    INDEX
    Explanations

    different types of animals, especially large ones

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific animal species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depreciation
    -0.76
     prescription
    -0.72
     billing
    -0.71
     deductible
    -0.70
     ingred
    -0.70
    Gate
    -0.69
     simultane
    -0.69
     testim
    -0.68
     Vanity
    -0.68
     sincerity
    -0.68
    POSITIVE LOGITS
    birds
    1.39
    fish
    1.25
     beetle
    1.23
     deer
    1.21
     beetles
    1.20
     turtles
    1.18
     squirrel
    1.16
     monkeys
    1.15
     crabs
    1.14
     rodents
    1.13
    Act Density 0.285%

    No Known Activations