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

    Neuronpedia

    INDEX
    Explanations

    the frequency and intensity of the word "too" in various contexts

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

    many, few, or often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.58
     GenerationType
    -0.52
    DoubleQuotes
    -0.50
     الرياضيه
    -0.47
    Datuak
    -0.46
     Hints
    -0.46
    stylers
    -0.45
    ">//
    -0.45
     ujednoznacz
    -0.44
    Derbyniad
    -0.43
    POSITIVE LOGITS
     allzu
    0.43
    太多的
    0.42
     mnoho
    0.38
     препратки
    0.35
    太多
    0.34
     vieler
    0.33
    SequentialGroup
    0.33
     frequ
    0.32
    ctez
    0.32
     many
    0.32
    Act Density 0.054%

    No Known Activations