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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating increases or changes in quantities

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

    Multiplication or scaling factors

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by times or fold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.88
    ContentLoaded
    -0.54
    Geplaatst
    -0.50
    IntoConstraints
    -0.50
     bast
    -0.50
    qrstuvwxyz
    -0.49
     BeautifulSoup
    -0.49
    conio
    -0.49
    __":
    -0.47
    chila
    -0.46
    POSITIVE LOGITS
     double
    1.39
     threefold
    1.37
     times
    1.34
     twice
    1.33
     quadruple
    1.30
     twofold
    1.29
     triple
    1.28
    double
    1.27
     DOUBLE
    1.22
    倍
    1.21
    Act Density 0.549%

    No Known Activations