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

    Neuronpedia

    INDEX
    Explanations

    references to diversity or different types of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sst
    -0.16
    tings
    -0.14
     loft
    -0.14
    _barrier
    -0.14
    ings
    -0.14
    mong
    -0.14
    acon
    -0.14
    eters
    -0.14
     most
    -0.14
    provided
    -0.14
    POSITIVE LOGITS
     kinds
    0.18
    -times
    0.17
    ccione
    0.15
    iating
    0.15
    ãĢħ
    0.15
    ly
    0.15
    iability
    0.15
    ials
    0.15
     sorts
    0.14
    ãĤ§
    0.14
    Act Density 0.018%

    No Known Activations