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

    Neuronpedia

    INDEX
    Explanations

    references to specific elements or concepts in relationships and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sund
    -0.17
    otal
    -0.15
     spoiled
    -0.15
    £p
    -0.15
    .Singleton
    -0.15
    ipa
    -0.15
    wit
    -0.15
     spo
    -0.14
    ut
    -0.14
    Tap
    -0.14
    POSITIVE LOGITS
     springfox
    0.17
    serter
    0.16
    ampo
    0.15
    stell
    0.15
    ÄĻk
    0.15
     Ukra
    0.14
    WindowState
    0.14
     menn
    0.14
    ineTransform
    0.13
    epend
    0.13
    Act Density 0.001%

    No Known Activations