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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gad
    -0.71
     Forth
    -0.69
     Pegasus
    -0.68
     Rhodes
    -0.64
     Chop
    -0.61
     Wellington
    -0.61
     JFK
    -0.60
    owship
    -0.58
     Jennings
    -0.58
     Highlands
    -0.58
    POSITIVE LOGITS
    âĢ
    1.89
     âĢ
    1.36
    ï¸ı
    1.34
    Ò
    1.27
    â
    1.24
    âĢł
    1.22
    âĶ
    1.19
    ãĢ
    1.19
    Í
    1.19
    »
    1.18
    Act Density 0.178%

    No Known Activations