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

    Neuronpedia

    INDEX
    Explanations

    references to dinosaurs

    oai_token-act-pair · gpt-3.5-turbo

    references to dinosaurs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Recommend
    -0.79
    puff
    -0.71
    pring
    -0.70
    OND
    -0.68
    76561
    -0.67
    ndra
    -0.67
    Baltimore
    -0.66
    OA
    -0.65
    aspx
    -0.65
     Agents
    -0.64
    POSITIVE LOGITS
    osaurs
    1.77
    osaurus
    1.24
    arium
    0.97
     dinosaurs
    0.92
     fossils
    0.90
     dinosaur
    0.88
    ocide
    0.87
    brate
    0.85
    inosaur
    0.82
     Jurassic
    0.81
    Act Density 0.036%

    No Known Activations