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

    Neuronpedia

    INDEX
    Explanations

    specific numeric quantities and measurements related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensa
    -0.19
    abb
    -0.15
    671
    -0.15
    adele
    -0.15
    naire
    -0.14
    oste
    -0.14
    abad
    -0.14
    asan
    -0.14
    à¹Īาà¸ĩà¹Ĩ
    -0.14
    131
    -0.13
    POSITIVE LOGITS
     per
    0.28
     needed
    0.17
    =len
    0.17
    /km
    0.17
     fewer
    0.17
    :number
    0.16
    _per
    0.16
    needed
    0.16
     ÑĩиÑģло
    0.16
     má»Ĺi
    0.16
    Act Density 0.228%

    No Known Activations