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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by possessive nouns

    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
    iatus
    -0.86
    ukemia
    -0.86
    leneck
    -0.70
    tsy
    -0.70
    odiac
    -0.69
    boxing
    -0.69
    ovych
    -0.68
    warts
    -0.67
    flix
    -0.66
    emetery
    -0.65
    POSITIVE LOGITS
     sparing
    1.00
     levers
    0.99
     newfound
    0.93
     wisely
    0.89
     GOODMAN
    0.86
     restroom
    0.85
     leverage
    0.81
     resources
    0.81
     liber
    0.80
     brakes
    0.80
    Act Density 0.188%

    No Known Activations