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

    Neuronpedia

    INDEX
    Explanations

    references to rewards, bonuses, and incentives related to tasks or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "reward", "bonus", or "incentive"

    np_acts-logits-general · gemini-2.0-flash

    reward and incentive payments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.84
    DeleteBehavior
    -0.83
     Roskov
    -0.79
    发表于
    -0.74
     فريبيس
    -0.72
     noires
    -0.71
    complexContent
    -0.70
     gynhyrchwyd
    -0.70
    تقاوى
    -0.70
    BeginContext
    -0.67
    POSITIVE LOGITS
     reward
    1.71
     rewards
    1.67
     incentives
    1.54
     Reward
    1.38
     incentive
    1.35
    Reward
    1.33
     Rewards
    1.32
    reward
    1.32
    Rewards
    1.30
    rewards
    1.27
    Act Density 0.292%

    No Known Activations