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

    Neuronpedia

    INDEX
    Explanations

    references to different types of primates such as apes, gorillas, and primates in general

    oai_token-act-pair · gpt-3.5-turbo

    references to apes and gorillas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gren
    -0.80
    WIND
    -0.71
    tor
    -0.71
    Nap
    -0.70
    tw
    -0.69
    ttp
    -0.68
    vy
    -0.66
    spring
    -0.66
    mph
    -0.66
    demand
    -0.66
    POSITIVE LOGITS
     apes
    1.26
     chimpanzees
    1.24
     primates
    1.13
     gorilla
    1.10
    zee
    1.05
     Haram
    1.04
    zees
    1.00
     chimpan
    1.00
     ape
    0.93
     monkeys
    0.92
    Act Density 0.013%

    No Known Activations