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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to categorization, particularly in contexts of agreement, financial analysis, and weight classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gloss
    -0.14
    lint
    -0.14
    HING
    -0.14
    มà¸ķ
    -0.14
    ahl
    -0.13
    enames
    -0.13
    logan
    -0.13
    ůl
    -0.13
    _Interface
    -0.13
     Deadline
    -0.13
    POSITIVE LOGITS
     category
    0.57
    category
    0.43
     categories
    0.38
     bracket
    0.37
     categorie
    0.35
     каÑĤегоÑĢ
    0.35
     categoria
    0.35
    -category
    0.34
     Category
    0.34
    .category
    0.34
    Act Density 0.124%

    No Known Activations