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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to skills and qualifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    FACE
    -0.65
    fall
    -0.61
    thur
    -0.60
    fest
    -0.58
     Mandela
    -0.57
    ween
    -0.57
    phy
    -0.56
    ame
    -0.56
    oter
    -0.56
    iphany
    -0.56
    POSITIVE LOGITS
     professionals
    0.90
     workforce
    0.83
     instructors
    0.75
     interpre
    0.68
     workers
    0.67
     citiz
    0.67
     personnel
    0.66
     nursing
    0.65
     working
    0.65
     professional
    0.65
    Act Density 12.240%

    No Known Activations