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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     increa
    -3.20
     inev
    -3.15
     effe
    -3.08
     affor
    -3.06
     emphat
    -2.99
     fta
    -2.98
     accla
    -2.98
     fuf
    -2.98
     reluct
    -2.96
     unden
    -2.89
    POSITIVE LOGITS
    <bos>
    2.46
    .
    0.93
      
    0.85
    。
    0.84
    中
    0.82
    ;
    0.82
          
    0.80
    ,
    0.80
       
    0.80
        
    0.80
    Act Density 0.888%

    No Known Activations