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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical values and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ben
    -0.16
    hell
    -0.15
    nof
    -0.14
    hed
    -0.14
    عاÙĦ
    -0.13
    uter
    -0.13
    Re
    -0.13
    hrad
    -0.13
    po
    -0.13
    ecom
    -0.13
    POSITIVE LOGITS
    rike
    0.15
     bergen
    0.15
    kest
    0.15
     Wahl
    0.15
    fold
    0.14
    LEGRO
    0.14
     deposit
    0.14
    ×Ļ
    0.14
    DataExchange
    0.13
    appings
    0.13
    Act Density 0.025%

    No Known Activations