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

    Neuronpedia

    INDEX
    Explanations

    personal possessive pronouns and verbs indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     è£ıè¦ļéĨĴ
    -0.67
     departures
    -0.66
    ascular
    -0.66
    ========
    -0.66
     intervening
    -0.65
    lihood
    -0.65
    jri
    -0.64
    ETHOD
    -0.64
    DonaldTrump
    -0.63
    crit
    -0.63
    POSITIVE LOGITS
     wore
    1.11
     stole
    1.08
     bought
    1.06
     purchased
    1.03
     invented
    0.97
     crafted
    0.91
     borrowed
    0.89
     fashioned
    0.88
     inherited
    0.88
     planted
    0.85
    Act Density 0.179%

    No Known Activations