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

    Neuronpedia

    INDEX
    Explanations

    key themes and critical components in discussions about responsibility and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maps
    -0.15
     budgets
    -0.14
    acades
    -0.14
    arrays
    -0.14
     attempt
    -0.14
    DisplayStyle
    -0.14
     Arrays
    -0.13
    Profiles
    -0.13
    Controllers
    -0.13
    _profiles
    -0.13
    POSITIVE LOGITS
     things
    0.47
     elements
    0.40
     items
    0.39
     aspects
    0.36
     features
    0.35
    things
    0.33
     activities
    0.32
     stuff
    0.32
     components
    0.31
     topics
    0.31
    Act Density 0.869%

    No Known Activations