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

    Neuronpedia

    INDEX
    Explanations

    expressions related to receiving or demanding attention or action from others

    oai_token-act-pair · gpt-3.5-turbo

    references to the collective pronoun "us."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fect
    -0.62
    Reilly
    -0.62
    aryl
    -0.59
     Levine
    -0.58
    stick
    -0.57
    Offic
    -0.56
    tein
    -0.55
     ME
    -0.55
    inois
    -0.54
    endra
    -0.54
    POSITIVE LOGITS
    selves
    1.21
     ourselves
    1.11
    hers
    1.06
     selves
    0.94
    aning
    0.86
    ury
    0.85
    urious
    0.84
    urers
    0.82
    ern
    0.82
     mortals
    0.80
    Act Density 0.085%

    No Known Activations