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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wrap
    -0.83
    yang
    -0.79
    pher
    -0.75
    avis
    -0.73
    rov
    -0.73
    bender
    -0.72
    etz
    -0.71
    inctions
    -0.70
    olkien
    -0.70
    daq
    -0.70
    POSITIVE LOGITS
     own
    1.70
     favorite
    1.43
     favourite
    1.36
    selves
    1.18
     beloved
    1.15
     ancestors
    1.15
     surroundings
    1.13
     friends
    1.11
     hometown
    1.11
     thoughts
    1.10
    Act Density 1.169%

    No Known Activations