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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to categorization and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dds
    -0.15
    ůl
    -0.15
    otland
    -0.15
    ahlen
    -0.14
    OutOfBoundsException
    -0.13
    ĶåĽŀ
    -0.13
    eldo
    -0.13
    æµİ
    -0.12
    ARRIER
    -0.12
    HWND
    -0.12
    POSITIVE LOGITS
     category
    1.27
     categories
    1.12
     Category
    1.05
    category
    1.03
    Category
    1.00
     Categories
    0.98
    -category
    0.94
    Categories
    0.91
     CATEGORY
    0.91
    categories
    0.90
    Act Density 0.306%

    No Known Activations