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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of dinosaurs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dinosaur" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OA
    -0.79
    Recommend
    -0.72
    lining
    -0.70
    reen
    -0.66
    ple
    -0.66
    aspx
    -0.65
    azel
    -0.64
    arters
    -0.64
    OND
    -0.62
    Chicago
    -0.62
    POSITIVE LOGITS
    osaurs
    1.74
    osaurus
    1.30
     dinosaur
    1.18
     dinosaurs
    1.17
    arium
    0.97
     Dinosaur
    0.93
     Jurassic
    0.93
     fossils
    0.91
    ĸļ
    0.90
    inosaur
    0.87
    Act Density 0.015%

    No Known Activations