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

    Neuronpedia

    INDEX
    Explanations

    elements related to updates or enhancements in systems and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {{↵
    -0.19
     kalp
    -0.15
    xdc
    -0.15
    ohana
    -0.14
    .EventType
    -0.14
     vite
    -0.14
    maj
    -0.14
    YTE
    -0.13
    .foundation
    -0.13
    orris
    -0.13
    POSITIVE LOGITS
     instead
    0.24
    instead
    0.20
     Instead
    0.16
    Instead
    0.16
     previously
    0.16
    midd
    0.15
    лÑİ
    0.15
    ault
    0.15
     again
    0.15
    luet
    0.14
    Act Density 0.582%

    No Known Activations