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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "you" and its variations, indicating a focus on direct address or engagement with the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     are
    -0.20
    leston
    -0.19
     estão
    -0.16
     EITHER
    -0.16
    ÑİÑĤ
    -0.16
    DON
    -0.15
    mani
    -0.15
     имеÑİÑĤ
    -0.14
    plash
    -0.14
     either
    -0.14
    POSITIVE LOGITS
     guys
    0.26
     ever
    0.22
     suppose
    0.19
     remember
    0.19
     remembers
    0.18
     sometimes
    0.17
     perch
    0.17
    ever
    0.17
     Guys
    0.17
     Remember
    0.17
    Act Density 0.074%

    No Known Activations