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

    Neuronpedia

    INDEX
    Explanations

    new model names and features in automotive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ithub
    -0.15
    алÑİ
    -0.15
    INCLUDED
    -0.13
    ERGE
    -0.13
    atos
    -0.13
    ache
    -0.13
     unus
    -0.13
     uninstall
    -0.13
     Roose
    -0.13
     duplex
    -0.13
    POSITIVE LOGITS
     fac
    0.23
     badge
    0.20
     spy
    0.20
    badge
    0.19
     model
    0.19
    spy
    0.19
     deb
    0.18
     production
    0.18
     моделÑĮ
    0.18
     Badge
    0.18
    Act Density 0.078%

    No Known Activations