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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "appropriate" and variations thereof, indicating a focus on suitability or correctness in context

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

    appropriate usage for context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    -0.46
    liner
    -0.38
    жалуйста
    -0.37
     getCity
    -0.36
    scrollY
    -0.36
    ImageContext
    -0.36
    execSQL
    -0.36
    MultipartFile
    -0.35
     Consumo
    -0.34
     deleteUser
    -0.34
    POSITIVE LOGITS
    الحياه
    0.61
    ufficio
    0.52
    nappropriate
    0.50
    Diwedd
    0.49
    èze
    0.49
     adjustments
    0.48
    HasColumnType
    0.48
     safeguards
    0.47
     Apa
    0.47
    Inappropriate
    0.47
    Act Density 0.012%

    No Known Activations