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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "you" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the second person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.89
    enges
    -0.80
    ipal
    -0.70
    entimes
    -0.67
    20439
    -0.65
    tains
    -0.64
    ftime
    -0.64
    £ı
    -0.64
    assemb
    -0.64
    resources
    -0.63
    POSITIVE LOGITS
    're
    1.54
     guys
    1.27
    've
    1.18
    'll
    1.16
     gotta
    1.13
     bastard
    1.07
     wanna
    1.06
     know
    1.03
     idiots
    0.99
     guessed
    0.98
    Act Density 0.160%

    No Known Activations