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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically names likely associated with power dynamics and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to characters, particularly those associated with the theme of tyranny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.83
    manship
    -0.80
     Ou
    -0.78
    Reviewer
    -0.77
    PRESS
    -0.74
    )=(
    -0.73
    EngineDebug
    -0.73
    Offline
    -0.69
     Investors
    -0.69
    PUT
    -0.68
    POSITIVE LOGITS
    anny
    1.11
    rell
    1.05
     tyr
    1.01
     Tyr
    0.95
    acious
    0.90
    rible
    0.89
     Lann
    0.86
    anus
    0.85
    oshenko
    0.85
    ont
    0.84
    Act Density 0.017%

    No Known Activations