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

    Neuronpedia

    INDEX
    Explanations

    SQL commands and syntax related to selecting and counting unique items from datasets

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

    unique items and SQL SELECT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.59
     يتيمه
    -0.55
    islation
    -0.50
    zzleHttp
    -0.48
     Eſ
    -0.46
    تفصیلات
    -0.46
    おまけ
    -0.45
    pecabe
    -0.44
    -0.44
    ñores
    -0.44
    POSITIVE LOGITS
     unique
    2.70
    unique
    2.36
     Unique
    2.23
    Unique
    2.22
     UNIQUE
    2.17
     uniqueness
    2.14
     uniques
    2.05
     unik
    1.91
     unieke
    1.91
    UNIQUE
    1.87
    Act Density 0.227%

    No Known Activations