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

    Neuronpedia

    INDEX
    Explanations

    references to to-do lists and productivity tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elia
    -0.17
    zik
    -0.15
     underlying
    -0.15
     Nested
    -0.15
     Tham
    -0.15
    RAR
    -0.15
    vio
    -0.14
    156
    -0.14
    aise
    -0.14
    238
    -0.14
    POSITIVE LOGITS
    iversit
    0.18
    iew
    0.17
    afort
    0.15
    EATURE
    0.15
    .gc
    0.15
    leine
    0.14
    oker
    0.14
    ieval
    0.14
    RYPT
    0.13
    ë¥
    0.13
    Act Density 0.094%

    No Known Activations