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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns ('I')

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and related self-referential expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pires
    -0.65
    Materials
    -0.59
     Georgian
    -0.57
     Gale
    -0.57
     optics
    -0.57
     Uriel
    -0.57
    eers
    -0.57
    ieves
    -0.56
     Leban
    -0.55
     us
    -0.53
    POSITIVE LOGITS
    'm
    1.67
     am
    1.27
    verson
    0.99
    aido
    0.96
    ggy
    0.92
    xtap
    0.89
    ANA
    0.89
    've
    0.89
     myself
    0.87
    Am
    0.86
    Act Density 0.189%

    No Known Activations