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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols used in written languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     + 
    -0.60
    ────────
    -0.59
       
    -0.57
    

    -0.57
     = 
    -0.56
    . 
    -0.56
     
    -0.55
        
    -0.54
      
    -0.54
    addContainerGap
    -0.54
    POSITIVE LOGITS
    ्
    0.58
    ь
    0.57
    ્
    0.56
    ্
    0.55
    े
    0.54
    ่
    0.54
    ं
    0.53
    ้
    0.52
     setIs
    0.51
    ि
    0.51
    Act Density 0.501%

    No Known Activations