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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns indicating possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronouns "I" and "my"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meier
    -0.72
    olute
    -0.68
    neapolis
    -0.67
    rencies
    -0.66
    nesota
    -0.66
     kW
    -0.65
    itude
    -0.65
    ouston
    -0.65
    imil
    -0.65
    itect
    -0.63
    POSITIVE LOGITS
    bara
    0.81
     Cats
    0.69
     âĻ
    0.68
    RL
    0.66
     presume
    0.66
     brig
    0.65
    ahar
    0.65
    oan
    0.63
    udic
    0.63
    ona
    0.63
    Act Density 0.395%

    No Known Activations