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

    Neuronpedia

    INDEX
    Explanations

    terms related to categories and classifications in research or data contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥
    -0.14
    лин
    -0.14
    _vue
    -0.14
    <Unit
    -0.13
    äs
    -0.13
    ¸
    -0.13
    .jd
    -0.13
    à¸ĩาà¸Ļ
    -0.13
    }elseif
    -0.13
    ofi
    -0.13
    POSITIVE LOGITS
     Class
    0.35
     category
    0.33
     class
    0.33
     grade
    0.31
     rating
    0.31
     Category
    0.30
     Grade
    0.30
     ratings
    0.28
    Category
    0.27
    category
    0.27
    Act Density 0.138%

    No Known Activations