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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns 'you' and contractions like 'you're' and 'you've'

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "you" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Negative Logits
    dimension
    -0.95
    arget
    -0.86
    hyde
    -0.85
     Dimension
    -0.85
    capacity
    -0.83
    Balt
    -0.81
    terness
    -0.81
    ausible
    -0.81
     Ambro
    -0.80
     Different
    -0.80
    POSITIVE LOGITS
    're
    1.87
    've
    1.52
     guys
    1.34
     guessed
    1.31
     want
    1.29
     wanna
    1.28
     wish
    1.27
    ever
    1.20
     hear
    1.19
    'll
    1.19
    Act Density 0.391%

    No Known Activations