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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to science, research, and experiments

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with time and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atism
    -0.80
     wardrobe
    -0.74
     estate
    -0.74
     vigilante
    -0.73
     condo
    -0.69
     bung
    -0.69
     hust
    -0.69
     apost
    -0.67
    lections
    -0.67
     enforce
    -0.67
    POSITIVE LOGITS
    Researchers
    1.65
    Scientists
    1.53
    Explore
    1.46
    Abstract
    1.33
    Study
    1.25
     Researchers
    1.24
    Methods
    1.23
    RESULTS
    1.18
    Professor
    1.14
    Research
    1.14
    Act Density 0.325%

    No Known Activations