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

    Neuronpedia

    INDEX
    Explanations

    repetitive mentions of the second person pronoun "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    you followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.34
     oeil
    -0.32
    $=$
    -0.32
     McE
    -0.30
     &
    -0.30
     lendemain
    -0.29
    ậc
    -0.27
     itself
    -0.27
     McEl
    -0.27
    <h2>
    -0.26
    POSITIVE LOGITS
    <unused74>
    0.98
    <unused41>
    0.98
    [@BOS@]
    0.98
    <pad>
    0.98
    <unused43>
    0.98
    <unused14>
    0.98
    <unused28>
    0.98
    <unused16>
    0.98
    <unused3>
    0.98
    <unused8>
    0.98
    Act Density 0.022%

    No Known Activations