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

    Neuronpedia

    INDEX
    Explanations

    source code elements related to configuration settings or constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uada
    -0.16
    EntityType
    -0.14
     rele
    -0.14
    .EventHandler
    -0.14
    AFE
    -0.14
    anner
    -0.13
    alin
    -0.13
     Nab
    -0.13
     Wallace
    -0.13
    afe
    -0.13
    POSITIVE LOGITS
    ools
    0.19
    ÏģοÏį
    0.16
    ntag
    0.16
    pag
    0.16
    ilton
    0.14
    reek
    0.14
    ool
    0.14
    еле
    0.13
    شت
    0.13
    ilon
    0.13
    Act Density 0.038%

    No Known Activations