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

    Neuronpedia

    INDEX
    Explanations

    structural elements and symbols in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -1.50
    _
    -0.85
        
    -0.84
    (
    -0.80
    <
    -0.77
    -0.76
      
    -0.76
    	
    -0.71
       
    -0.70
          
    -0.68
    POSITIVE LOGITS
    <unused14>
    2.27
    <unused68>
    2.27
    <unused52>
    2.27
    <unused3>
    2.25
    <unused79>
    2.25
    [@BOS@]
    2.25
    <unused8>
    2.25
    <unused16>
    2.25
    <unused17>
    2.23
    <unused21>
    2.23
    Act Density 0.522%
    No Known Activations