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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the practice or act of doing something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    worms
    -0.84
    gin
    -0.80
    este
    -0.76
    gow
    -0.76
    eele
    -0.72
    ilight
    -0.68
    nette
    -0.68
    sea
    -0.67
    mented
    -0.66
    hyde
    -0.66
    POSITIVE LOGITS
     practiced
    0.79
     practice
    0.78
     regimen
    0.77
    ually
    0.76
    itual
    0.75
     Practices
    0.74
     pract
    0.72
     Practice
    0.72
     practices
    0.71
    uality
    0.70
    Act Density 0.795%

    No Known Activations