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

    Neuronpedia

    INDEX
    Explanations

    mention of careers and related professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.57
     injector
    -0.51
     Cours
    -0.50
    Cours
    -0.48
     Instructions
    -0.48
    makeConstraints
    -0.48
     المعيارى
    -0.47
     BeautifulSoup
    -0.47
     Woodstock
    -0.47
    -------------</
    -0.46
    POSITIVE LOGITS
     career
    0.71
    Career
    0.70
     carreira
    0.69
    Carreira
    0.65
    career
    0.63
     careers
    0.63
     Career
    0.63
     carriera
    0.63
     karier
    0.59
     Karriere
    0.58
    Act Density 0.134%

    No Known Activations