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

    Neuronpedia

    INDEX
    Explanations

    references to social or political structures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "the."

    np_acts-logits-general · gemini-2.0-flash

    the collection or category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieux
    -0.76
     vœux
    -0.67
     Juifs
    -0.66
     épaules
    -0.65
     bienfaits
    -0.64
     consommateurs
    -0.62
     touristes
    -0.59
     âmes
    -0.57
    ImageContext
    -0.57
    RegressionTest
    -0.56
    POSITIVE LOGITS
     ones
    1.10
     stuff
    0.98
     creations
    0.84
     projects
    0.83
     stories
    0.82
     multitude
    0.80
     decisions
    0.80
     moindre
    0.79
     Vielzahl
    0.79
    一个个
    0.78
    Act Density 0.484%

    No Known Activations