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

    Neuronpedia

    INDEX
    Explanations

    references to human-related aspects, especially focusing on human rights and the human experience

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights and the concept of humanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mods
    -0.76
    tie
    -0.70
     Recipes
    -0.69
     Goes
    -0.68
    iques
    -0.65
    ops
    -0.64
    tesy
    -0.64
    exclusive
    -0.64
    ocket
    -0.63
    went
    -0.62
    POSITIVE LOGITS
     human
    3.54
    Human
    2.56
     Human
    2.53
    human
    2.51
     humans
    2.44
    humans
    1.91
     humanity
    1.85
     Humans
    1.84
     mammalian
    1.80
     humankind
    1.60
    Act Density 0.021%

    No Known Activations