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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their relevance in text structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.96
    matchCondition
    -0.96
     BoxDecoration
    -0.94
     MainAxisSize
    -0.92
    تقاوى
    -0.90
    styleType
    -0.89
    SourceChecksum
    -0.88
     Efq
    -0.88
    LookAnd
    -0.88
     snippetHide
    -0.88
    POSITIVE LOGITS
     (
    0.57
     then
    0.57
     if
    0.52
      
    0.51
     further
    0.51
     it
    0.50
    ↵
    0.49
     
    0.49
     which
    0.49
     and
    0.48
    Act Density 0.490%

    No Known Activations