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

    Neuronpedia

    INDEX
    Explanations

    mentions of high-quality items or products

    oai_token-act-pair · gpt-3.5-turbo

    references to high-quality products or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ften
    -0.75
    kens
    -0.69
     Hanson
    -0.66
    thur
    -0.64
    oths
    -0.63
     Zimmerman
    -0.63
     Thornton
    -0.62
     Zimmer
    -0.62
    psy
    -0.61
     Vikings
    -0.60
    POSITIVE LOGITS
     assurance
    1.09
     quality
    1.00
    Quality
    0.87
    smanship
    0.84
     materials
    0.79
     products
    0.79
     Quality
    0.79
     standards
    0.77
    quality
    0.77
     product
    0.77
    Act Density 0.019%

    No Known Activations