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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software or hardware optimization and analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     encomp
    -2.78
     depic
    -2.73
     reluct
    -2.68
     guarante
    -2.66
     volunte
    -2.61
     accla
    -2.60
     disagre
    -2.49
     increa
    -2.49
     emphat
    -2.46
     purcha
    -2.45
    POSITIVE LOGITS
     million
    0.78
      
    0.75
     billion
    0.72
     
    0.70
    则
    0.70
     млн
    0.69
       
    0.68
        
    0.68
    也
    0.68
    sum
    0.67
    Act Density 0.153%

    No Known Activations