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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reward systems and incentives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SuppressLint
    -0.46
     перено
    -0.43
    setVerticalGroup
    -0.42
     filter
    -0.40
    filter
    -0.40
    pivot
    -0.36
     Vor
    -0.36
    impres
    -0.35
    fitrión
    -0.35
    Capacidad
    -0.35
    POSITIVE LOGITS
     reward
    3.19
     rewards
    2.94
     Reward
    2.64
    reward
    2.58
     rewarded
    2.50
    Reward
    2.48
     Rewards
    2.44
    Rewards
    2.39
     récompense
    2.31
    rewards
    2.30
    Act Density 0.466%

    No Known Activations