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
    áf
    -0.17
    hiro
    -0.17
    bjerg
    -0.14
    uard
    -0.14
    iew
    -0.14
    ungan
    -0.14
    probably
    -0.13
     deliber
    -0.13
     Lon
    -0.13
     Gand
    -0.13
    POSITIVE LOGITS
    647
    0.17
    883
    0.16
     varsa
    0.16
    olit
    0.15
    اض
    0.15
    ä»Ķ
    0.15
     ever
    0.15
    è¿Ļæł·
    0.14
     hadn
    0.14
     fos
    0.14
    Act Density 0.119%

    No Known Activations