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

    Neuronpedia

    INDEX
    Explanations

    pronouns related to the audience or the speaker

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective "us."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lets
    -0.64
    fect
    -0.64
    tein
    -0.61
     CPC
    -0.58
    ussen
    -0.57
     livest
    -0.57
    Offic
    -0.56
     MAC
    -0.55
    stick
    -0.55
     chaired
    -0.55
    POSITIVE LOGITS
    selves
    1.20
    hers
    1.16
    ern
    0.91
    urers
    0.89
    aning
    0.89
     ourselves
    0.88
     selves
    0.85
    ury
    0.79
    urious
    0.79
    leep
    0.78
    Act Density 0.062%

    No Known Activations