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

    Neuronpedia

    INDEX
    Explanations

    mentions of human beings

    oai_token-act-pair · gpt-3.5-turbo

    references to "human beings" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etta
    -0.69
     Kitchen
    -0.66
    ORY
    -0.64
    CL
    -0.62
    Pop
    -0.61
    BALL
    -0.61
     Gillespie
    -0.61
     Soda
    -0.61
     Kerr
    -0.60
     Ridge
    -0.60
    POSITIVE LOGITS
     beings
    1.22
    terness
    0.93
     imperson
    0.87
    ĨĴ
    0.85
     Tradable
    0.84
     unworthy
    0.83
     sentient
    0.82
     rul
    0.81
     endowed
    0.80
     mortals
    0.80
    Act Density 0.010%

    No Known Activations