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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "we."

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

    we + verbaux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.54
     queſta
    -0.54
    Rüyada
    -0.53
     متعلقه
    -0.51
    ſchen
    -0.50
     Мексичка
    -0.50
     AVC
    -0.49
    üyada
    -0.48
    yng
    -0.48
    ſcher
    -0.48
    POSITIVE LOGITS
    ContentAlignment
    0.45
    点此举报
    0.39
    getDoctrine
    0.35
     comprender
    0.34
    řeba
    0.34
    算
    0.34
     ayı
    0.33
    打量
    0.33
     potře
    0.33
     čás
    0.32
    Act Density 0.075%

    No Known Activations