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

    Neuronpedia

    INDEX
    Explanations

    features related to language learning tools and user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resher
    -0.15
     пеÑĢе
    -0.14
    regs
    -0.14
    atra
    -0.14
    егоÑĢ
    -0.14
    ander
    -0.13
    uncture
    -0.13
    arta
    -0.13
    ãģ¶
    -0.13
    capacity
    -0.13
    POSITIVE LOGITS
     rewards
    0.35
     reward
    0.33
     progress
    0.28
     challenge
    0.28
     points
    0.28
     Rewards
    0.27
     earn
    0.27
     leaderboard
    0.27
     competition
    0.26
     rewarded
    0.26
    Act Density 0.116%

    No Known Activations