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

    Neuronpedia

    INDEX
    Explanations

    words related to communal spaces or shared experiences

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the term "Common."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     save
    -0.65
    istas
    -0.64
    laden
    -0.64
     guys
    -0.63
    edin
    -0.63
     erase
    -0.62
     saves
    -0.62
    ula
    -0.60
    iang
    -0.60
    Ð
    -0.60
    POSITIVE LOGITS
     Common
    3.91
    Common
    2.59
    common
    2.07
     Uncommon
    2.03
     common
    1.97
     commons
    1.64
    Uncommon
    1.43
     Rare
    1.34
     Commons
    1.23
     Popular
    1.12
    Act Density 0.020%

    No Known Activations