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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "You" and related phrases indicating direct address to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usher
    -0.16
    yny
    -0.15
     Uncomment
    -0.14
    urus
    -0.14
     numberWith
    -0.14
    undry
    -0.14
    浩
    -0.14
    asser
    -0.13
    rawer
    -0.13
    ÑĨенÑĤÑĢа
    -0.13
    POSITIVE LOGITS
     said
    0.20
     seem
    0.20
     mentioned
    0.18
     forgot
    0.18
     seemed
    0.18
     seems
    0.18
    mentioned
    0.18
     mileage
    0.17
     could
    0.17
     stated
    0.17
    Act Density 0.042%

    No Known Activations