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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "you" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atti
    -0.16
     itself
    -0.16
    nut
    -0.15
    andon
    -0.15
    store
    -0.14
     usted
    -0.14
    member
    -0.14
    foot
    -0.14
    line
    -0.13
    nb
    -0.13
    POSITIVE LOGITS
    ’re
    0.25
    ’ll
    0.24
    'll
    0.24
    're
    0.22
    ’ve
    0.21
    -même
    0.21
    've
    0.21
    nger
    0.20
    ’d
    0.20
    'd
    0.19
    Act Density 0.463%

    No Known Activations