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

    Neuronpedia

    INDEX
    Explanations

    words related to jobs or tasks that are exceptionally done

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     increa
    -1.58
     purcha
    -1.54
     fta
    -1.54
     impra
    -1.52
     strick
    -1.50
     depic
    -1.48
     reluct
    -1.46
     volunte
    -1.44
     inev
    -1.44
     affor
    -1.44
    POSITIVE LOGITS
    getItemId
    0.67
    fillRect
    0.62
    AndEndTag
    0.61
    AddHtmlAttribute
    0.59
     job
    0.59
    FromArgb
    0.58
     Paglinawan
    0.57
    Trotz
    0.56
     الاطلاع
    0.56
    Televis
    0.56
    Act Density 0.147%

    No Known Activations