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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific large animals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific large animal species, particularly elephants and tigers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucer
    -0.78
     member
    -0.75
    tor
    -0.73
     Member
    -0.73
    ame
    -0.68
    ident
    -0.68
    ICLE
    -0.67
     joint
    -0.67
    rator
    -0.67
     user
    -0.67
    POSITIVE LOGITS
     cows
    2.39
     chickens
    2.38
     elephants
    2.35
     dolphins
    2.25
     horses
    2.20
     goats
    2.08
     tigers
    2.05
     ducks
    2.00
     lions
    1.98
     monkeys
    1.98
    Act Density 0.037%

    No Known Activations