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

    Neuronpedia

    INDEX
    Explanations

    words that express opinion or expectation

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

    providing answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.47
    parsedMessage
    -0.47
    createStatement
    -0.45
    RenderAtEndOf
    -0.45
     zewnętrzne
    -0.45
    ismet
    -0.44
    敛
    -0.44
     attaque
    -0.44
    UrlResolution
    -0.43
     termica
    -0.43
    POSITIVE LOGITS
     answer
    0.59
    answer
    0.56
     answers
    0.56
    回答
    0.52
    Answer
    0.50
     Answer
    0.46
    ANSWER
    0.45
     ANSWER
    0.45
     answered
    0.44
     Answers
    0.43
    Act Density 0.221%

    No Known Activations