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

    Neuronpedia

    INDEX
    Explanations

    mentions of second-person pronouns, particularly focusing on "you"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lago
    -0.70
     Richmond
    -0.68
     Rhodes
    -0.66
     Political
    -0.64
     airs
    -0.63
    math
    -0.63
    acular
    -0.63
     Samoa
    -0.63
     Sabha
    -0.62
     Colonial
    -0.61
    POSITIVE LOGITS
    're
    1.39
    'll
    1.20
    've
    1.18
    hei
    1.00
    'd
    0.99
     guessed
    0.96
    tub
    0.94
     know
    0.94
     guys
    0.91
     can
    0.89
    Act Density 0.253%

    No Known Activations