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

    Neuronpedia

    INDEX
    Explanations

    references to the second person pronoun "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lok
    -0.15
    atti
    -0.15
    wers
    -0.14
    amp
    -0.14
    rang
    -0.13
    رÙģ
    -0.13
    idious
    -0.13
     byt
    -0.13
    iative
    -0.13
    rou
    -0.13
    POSITIVE LOGITS
    ’re
    0.21
    SELF
    0.19
    're
    0.17
    -même
    0.17
    ’ll
    0.16
    indsight
    0.16
    ’ve
    0.16
    zelf
    0.16
    /us
    0.16
    OSE
    0.15
    Act Density 0.467%

    No Known Activations