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

    Neuronpedia

    INDEX
    Explanations

    verbs related to improvement or enhancement

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

    improving something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.43
     numberOfRows
    -0.43
    atalog
    -0.42
     küche
    -0.42
    ucket
    -0.41
     bagels
    -0.41
     poto
    -0.40
     zodiac
    -0.40
    seasons
    -0.40
     dinos
    -0.40
    POSITIVE LOGITS
     improved
    0.82
     improves
    0.81
     Improved
    0.79
     Improves
    0.78
    Improve
    0.77
    Improved
    0.75
     Improve
    0.73
    improved
    0.73
     improve
    0.72
     Improving
    0.69
    Act Density 0.030%

    No Known Activations