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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns and verbs indicating thought or speculation

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate self-reference, particularly "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walton
    -0.64
    ources
    -0.63
    rising
    -0.62
     Clancy
    -0.61
    tions
    -0.61
     Uriel
    -0.61
     Pearson
    -0.60
     Roose
    -0.59
    psons
    -0.59
     Thrones
    -0.59
    POSITIVE LOGITS
    'm
    1.49
     am
    1.05
    've
    1.02
    verson
    0.99
    RL
    0.96
    ANA
    0.93
    'll
    0.91
    MAX
    0.90
     guess
    0.88
     myself
    0.87
    Act Density 0.171%

    No Known Activations