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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "you" in various contexts

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

    questions starting with did you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.59
     forState
    -0.47
     pleaſure
    -0.43
    exitRule
    -0.43
    parsedMessage
    -0.42
    awtextra
    -0.41
     meurt
    -0.40
     Мексичка
    -0.39
     ſtre
    -0.38
     purpoſe
    -0.38
    POSITIVE LOGITS
     anhydride
    0.52
    siapkan
    0.50
    illon
    0.49
     Missed
    0.48
    idental
    0.47
     getItemId
    0.46
     pungkasnya
    0.46
     Nested
    0.45
     Reported
    0.45
    Missed
    0.44
    Act Density 0.007%

    No Known Activations