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

    Neuronpedia

    INDEX
    Explanations

    topics related to recommendations or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.18
     th
    -0.14
    raph
    -0.14
    ,
    -0.14
    ifestyles
    -0.14
    uos
    -0.13
    227
    -0.13
     oc
    -0.13
     pau
    -0.13
    elfare
    -0.13
    POSITIVE LOGITS
     actionTypes
    0.18
    akers
    0.15
    fx
    0.15
    DataExchange
    0.14
    ITTE
    0.14
    à¹Ĥย
    0.14
    dbo
    0.14
    à¸ģรรม
    0.14
    orarily
    0.14
    à¸ĩาà¸Ļ
    0.14
    Act Density 0.166%

    No Known Activations