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

    Neuronpedia

    INDEX
    Explanations

    terms related to different kinds of entities like games, stores, languages, recipes, occupations, venues, ships, species, schools, sites, branches, phones, countries, foods, sites, councils, schools, businesses, celebrations, events, schools, and more

    oai_token-act-pair · gpt-3.5-turbo

    nouns that refer to various categories or classifications in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atever
    -0.62
    jee
    -0.62
    idan
    -0.61
     Sharing
    -0.61
     Spoon
    -0.58
    igun
    -0.58
    zh
    -0.58
     Fighters
    -0.56
    othy
    -0.56
    ww
    -0.56
    POSITIVE LOGITS
    mith
    0.88
     require
    0.78
     are
    0.78
     have
    0.77
     fared
    0.77
     specialize
    0.75
     succumbed
    0.75
     analysed
    0.75
     resorted
    0.74
    chool
    0.74
    Act Density 0.308%

    No Known Activations