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

    Neuronpedia

    INDEX
    Explanations

    pronouns that imply personal relationships or connections with others

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

    first-person and we statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.52
    twimg
    -0.49
     ExecuteAsync
    -0.49
    SourceChecksum
    -0.48
    最快更新
    -0.43
    hoeddwyd
    -0.41
    Kjelder
    -0.41
     Wikimedijinoj
    -0.40
    hyrchwyd
    -0.40
    ⤒
    -0.40
    POSITIVE LOGITS
    }{*}{
    0.54
    __":
    0.49
    torie
    0.49
    翼
    0.48
    brigens
    0.47
     pulleys
    0.46
    "")
    0.44
    RTHOOK
    0.44
    leby
    0.44
    ）
    0.44
    Act Density 0.201%

    No Known Activations