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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to rewards, tips, and incentives

    oai_token-act-pair · gpt-3.5-turbo

    references to rewards or incentives related to actions or information being provided

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    legraph
    -0.74
    pport
    -0.70
    soDeliveryDate
    -0.70
    limits
    -0.69
    pect
    -0.69
    types
    -0.65
    æĦ
    -0.65
    eda
    -0.63
    eneg
    -0.63
    ise
    -0.62
    POSITIVE LOGITS
     deeds
    1.11
     referrals
    1.04
     successes
    1.00
     completing
    0.99
     contributions
    0.99
     mistakes
    0.96
     discoveries
    0.92
     failures
    0.92
     conversions
    0.92
     actions
    0.90
    Act Density 0.238%

    No Known Activations