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

    Neuronpedia

    INDEX
    Explanations

    reward descriptions in a loyalty program

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rewards and incentives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [/
    -0.85
    .</
    -0.81
    </
    -0.79
    ".[
    -0.79
    "},"
    -0.77
     ®
    -0.74
    ||||
    -0.71
    %"
    -0.71
     </
    -0.70
    Minecraft
    -0.70
    POSITIVE LOGITS
     likewise
    1.14
     similarly
    1.00
     again
    0.96
     Again
    0.86
     also
    0.83
    again
    0.78
     another
    0.78
     additionally
    0.78
     Same
    0.77
     equally
    0.74
    Act Density 0.788%

    No Known Activations