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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "feature" and related concepts in the context of data analysis or machine learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     photolibrary
    -0.88
     pessoais
    -0.86
     Ankunft
    -0.86
     pregunto
    -0.85
     clearColor
    -0.85
     PVA
    -0.84
    Alp
    -0.83
     geboren
    -0.82
     nôtre
    -0.82
    ]^{-
    -0.81
    POSITIVE LOGITS
     features
    2.68
     feature
    2.55
     Features
    2.35
    features
    2.27
     Feature
    2.26
    Features
    2.23
    Feature
    2.19
    feature
    2.18
     FEATURE
    2.15
     FEATURES
    2.06
    Act Density 0.043%

    No Known Activations