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

    Neuronpedia

    INDEX
    Explanations

    numeric and symbolic formats indicative of time stamps, version numbers, or potentially structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.17
    enou
    -0.15
    ctica
    -0.15
    ToWorld
    -0.15
    _RTC
    -0.15
    Ñŀ
    -0.14
    vro
    -0.14
    EIF
    -0.14
    _macros
    -0.14
     punches
    -0.14
    POSITIVE LOGITS
     bulk
    0.16
    bulk
    0.16
    iefs
    0.15
     Cub
    0.15
     Crud
    0.14
    .opens
    0.13
    nger
    0.13
     aras
    0.13
    ast
    0.13
    trys
    0.13
    Act Density 0.156%

    No Known Activations