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

    Neuronpedia

    INDEX
    Explanations

    mentions of research studies and researchers

    oai_token-act-pair · gpt-3.5-turbo

    references to researchers or research activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tribal
    -0.71
    AAAA
    -0.64
     Valkyrie
    -0.63
     Judgment
    -0.61
     Maiden
    -0.60
    co
    -0.60
     Glory
    -0.58
     Passage
    -0.58
    Enough
    -0.57
     Territories
    -0.57
    POSITIVE LOGITS
    ynthesis
    1.00
    hran
    0.93
    sonian
    0.93
    paces
    0.90
    uggest
    0.88
    Researchers
    0.87
    essor
    0.86
     Researchers
    0.86
    ynt
    0.84
    natureconservancy
    0.83
    Act Density 0.036%

    No Known Activations