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

    Neuronpedia

    INDEX
    Explanations

    patterns of parentheses and special character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     includes
    -0.15
     Dot
    -0.15
    includes
    -0.14
     Di
    -0.14
     util
    -0.14
     text
    -0.14
     column
    -0.14
     part
    -0.14
     Des
    -0.14
     is
    -0.13
    POSITIVE LOGITS
    #define
    0.47
    define
    0.40
     define
    0.37
    (define
    0.35
    .define
    0.35
    å®ļä¹ī
    0.35
     definition
    0.34
    definition
    0.34
    	define
    0.34
    defined
    0.32
    Act Density 0.006%

    No Known Activations