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

    Neuronpedia

    INDEX
    Explanations

    phrases related to classification and categorization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MaterialApp
    -0.51
    ruptedException
    -0.51
    anny
    -0.51
    tanleria
    -0.50
    ModelState
    -0.50
     caros
    -0.47
    Herb
    -0.46
     éditoriale
    -0.46
     AssemblyTitle
    -0.46
    illies
    -0.45
    POSITIVE LOGITS
     classification
    1.12
     classifications
    1.01
     categories
    1.00
     classify
    0.93
     classifying
    0.92
     categor
    0.92
     classified
    0.92
     Classification
    0.91
     categorization
    0.91
     category
    0.90
    Act Density 0.524%

    No Known Activations