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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "us"

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective experience or perspective of a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    netflix
    -0.76
    ritz
    -0.68
    JUST
    -0.67
     CPC
    -0.67
    ussen
    -0.65
    fect
    -0.63
    oard
    -0.61
    ildo
    -0.59
    similar
    -0.59
    NetMessage
    -0.59
    POSITIVE LOGITS
    selves
    1.20
    hers
    1.00
    aning
    0.83
     eleph
    0.82
     selves
    0.79
    alg
    0.77
     ourselves
    0.74
    arily
    0.73
    atically
    0.72
    atic
    0.72
    Act Density 0.057%

    No Known Activations