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

    Neuronpedia

    INDEX
    Explanations

    first-person singular pronouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     totality
    -0.63
     Vald
    -0.61
     PTS
    -0.59
    illary
    -0.57
    terday
    -0.57
     Uriel
    -0.57
     Bever
    -0.56
    minster
    -0.56
     density
    -0.55
     membr
    -0.55
    POSITIVE LOGITS
    'm
    1.62
    've
    1.33
     am
    1.21
     guess
    1.21
     suppose
    1.19
    'll
    1.13
    'd
    1.08
     presume
    1.06
    verson
    1.00
    ronic
    0.99
    Act Density 0.305%

    No Known Activations