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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or questioning

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

    Conditional statements ("when", "if", "as")

    np_acts-logits-general · gemini-2.0-flash

    conditional clauses and sequence beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.60
    stdc
    -0.60
    useState
    -0.57
     nevertheless
    -0.56
    országban
    -0.56
    帖最后由
    -0.56
     useState
    -0.56
     assuredly
    -0.56
     quizá
    -0.56
    :+:
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.66
    RegressionTest
    0.56
    abestanden
    0.56
    $)$
    0.53
    IsContent
    0.52
    +#+#
    0.50
    \"></
    0.50
     )}$
    0.49
    //{
    0.48
    //}
    0.47
    Act Density 0.019%

    No Known Activations