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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "however" indicating contrasts or transitions in the text

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

    use of 'however'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.61
    ChildScrollView
    -0.60
     оригіналу
    -0.49
    NewReader
    -0.48
    ///</
    -0.43
    ApplicationTests
    -0.39
     것이다
    -0.39
     мәкал
    -0.38
    ")->
    -0.37
    ningarna
    -0.36
    POSITIVE LOGITS
     allora
    0.47
     CreateTagHelper
    0.46
     للاسماء
    0.45
     المعيارى
    0.45
     disambiguazione
    0.42
    ExecuteReader
    0.42
     THOUGH
    0.41
    mistry
    0.40
     though
    0.40
    SBATCH
    0.40
    Act Density 0.024%

    No Known Activations