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

    Neuronpedia

    INDEX
    Explanations

    profession-related words and issues, particularly focusing on education and societal accountability

    oai_token-act-pair · gpt-3.5-turbo

    references to education and community concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Puzz
    -0.66
    oret
    -0.64
     organisers
    -0.61
    racuse
    -0.60
    odder
    -0.60
     laure
    -0.58
    aples
    -0.57
     needles
    -0.57
     sidx
    -0.57
     Section
    -0.55
    POSITIVE LOGITS
    depending
    0.79
    .–
    0.77
     respectively
    0.75
     alike
    0.73
    etheless
    0.65
    .?
    0.63
     sandwic
    0.63
     depending
    0.62
     humankind
    0.62
    Enjoy
    0.62
    Act Density 0.541%

    No Known Activations