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

    Neuronpedia

    INDEX
    Explanations

    personal plural pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective "us" in the context of shared experiences or societal commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fect
    -0.74
     CPC
    -0.69
    tein
    -0.68
    lets
    -0.65
    ussen
    -0.62
     chaired
    -0.61
    ye
    -0.61
    majority
    -0.60
    inois
    -0.57
     Morty
    -0.56
    POSITIVE LOGITS
    selves
    1.26
    hers
    1.14
    ern
    0.99
    aning
    0.90
     selves
    0.87
     ourselves
    0.85
     eleph
    0.83
    leep
    0.79
    alg
    0.73
    ages
    0.72
    Act Density 0.061%

    No Known Activations