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
    New Auto-Interp
    Negative Logits
    pring
    -0.68
    OND
    -0.61
    ndra
    -0.59
    bie
    -0.57
    aspx
    -0.55
     Agents
    -0.55
    Recommend
    -0.54
    Baltimore
    -0.54
    arters
    -0.53
    dan
    -0.52
    POSITIVE LOGITS
    osaurs
    1.41
    osaurus
    1.08
    arium
    0.87
     dinosaurs
    0.79
     fossils
    0.74
     dinosaur
    0.73
    brate
    0.69
    ocide
    0.68
     skeletons
    0.68
    aurus
    0.68
    Act Density 7.965%

    No Known Activations