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

    Neuronpedia

    INDEX
    Explanations

    terms related to rewards and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .*")]
    -0.73
    WebRequest
    -0.73
     surla
    -0.71
    LookAnd
    -0.70
    JvmStatic
    -0.70
    UIControlState
    -0.68
    Enlaces
    -0.67
     تعدى
    -0.67
     papyrus
    -0.66
    BeginContext
    -0.64
    POSITIVE LOGITS
     reward
    1.66
     rewards
    1.58
     Reward
    1.49
     Rewards
    1.42
     rewarded
    1.40
    reward
    1.38
    Reward
    1.37
    Rewards
    1.30
     rewarding
    1.16
    rewards
    1.14
    Act Density 0.125%

    No Known Activations