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

    Neuronpedia

    INDEX
    Explanations

    references to specific car models and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ote
    -0.14
    artner
    -0.14
     paren
    -0.14
     Airbnb
    -0.14
    STEM
    -0.14
     Moore
    -0.13
    aso
    -0.13
     Lenovo
    -0.13
    etty
    -0.13
     Oswald
    -0.13
    POSITIVE LOGITS
     model
    0.29
     models
    0.26
    model
    0.24
    -model
    0.23
    models
    0.23
     fac
    0.21
     production
    0.21
     modelo
    0.21
     моделÑĮ
    0.21
     modèle
    0.21
    Act Density 0.044%

    No Known Activations