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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members, especially aunts or uncles

    oai_token-act-pair · gpt-3.5-turbo

    references to familial or communal entities, particularly "aunts" and "parishes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tz
    -0.86
    cling
    -0.65
    MET
    -0.63
    matically
    -0.63
    ppo
    -0.62
    HEAD
    -0.62
     Poster
    -0.62
    lli
    -0.60
    smoking
    -0.60
     headsets
    -0.59
    POSITIVE LOGITS
    nect
    1.06
    emouth
    1.05
    iary
    1.03
    sylvania
    1.02
    ette
    0.98
    mares
    0.94
    uary
    0.93
    ery
    0.89
    eenth
    0.89
    iversary
    0.87
    Act Density 0.119%

    No Known Activations