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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the amount of time spent on activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignoire
    -0.61
     Maiden
    -0.56
    ској
    -0.55
    OPH
    -0.53
    krad
    -0.51
    schule
    -0.50
     Weighted
    -0.50
    ÉM
    -0.49
     Mascot
    -0.49
    Slight
    -0.49
    POSITIVE LOGITS
     spent
    1.25
    Spent
    1.25
     Spent
    1.22
     spend
    1.16
    spent
    1.14
     spends
    1.12
     spending
    1.10
     Spend
    1.10
    Spend
    1.09
    Spending
    1.08
    Act Density 0.158%

    No Known Activations