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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing improvement or increase over time

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

    increasing or decreasing quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.64
    MLLoader
    -0.63
    __":
    -0.56
     שוליים
    -0.55
     ***!
    -0.55
    GEBURTSDATUM
    -0.54
    webElementXpaths
    -0.53
     հղումներ
    -0.51
     EconPapers
    -0.50
     Baillargeon
    -0.50
    POSITIVE LOGITS
     gradually
    0.85
     progressively
    0.85
     increasingly
    0.84
    越来越
    0.76
     Gradually
    0.75
     dần
    0.74
     slowly
    0.70
     progressivement
    0.68
     Slowly
    0.66
    Slowly
    0.66
    Act Density 0.352%

    No Known Activations