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

    the word "dinosaur" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Recommend
    -0.73
    OND
    -0.72
    76561
    -0.70
    pring
    -0.68
    ndra
    -0.67
    aspx
    -0.67
    arters
    -0.64
     Morse
    -0.64
    ple
    -0.64
    puff
    -0.64
    POSITIVE LOGITS
    osaurs
    1.67
    osaurus
    1.19
     dinosaurs
    1.03
    arium
    1.03
     dinosaur
    0.94
     fossils
    0.90
    inosaur
    0.83
    aurus
    0.82
    brate
    0.79
    ocide
    0.77
    Act Density 0.021%

    No Known Activations