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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Subject
    -0.82
    daq
    -0.80
     Spiel
    -0.79
    Trend
    -0.77
     Difference
    -0.73
     Majority
    -0.73
     Unsure
    -0.72
    Spoiler
    -0.71
     Trader
    -0.70
    netflix
    -0.70
    POSITIVE LOGITS
     own
    1.48
     contemporaries
    1.07
     predecessors
    1.06
     classmates
    1.04
     colleagues
    1.04
     favorite
    0.99
     coworkers
    0.97
     favourite
    0.95
     teammates
    0.95
     peers
    0.94
    Act Density 0.071%

    No Known Activations