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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "me" and its variants in conversations

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

    pronouns; foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithData
    -0.46
     Rück
    -0.41
    ()}}
    -0.41
     puro
    -0.39
     native
    -0.39
    :])
    -0.37
     esti
    -0.36
    Ingredienti
    -0.35
     πα
    -0.35
     background
    -0.35
    POSITIVE LOGITS
    Меня
    0.62
    IntoConstraints
    0.60
     itſelf
    0.60
    ConstraintMaker
    0.58
    IsMutable
    0.58
     myſelf
    0.56
    RSpec
    0.56
     themſelves
    0.56
     ویکی‌پدی
    0.56
    Билгалдахарш
    0.55
    Act Density 0.019%

    No Known Activations