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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to return policies and customer service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stable
    -0.58
     répartition
    -0.49
    stable
    -0.49
     jár
    -0.47
     Sandwich
    -0.46
     Stable
    -0.46
    Stable
    -0.46
     stabilize
    -0.46
     stabilized
    -0.45
     stabile
    -0.45
    POSITIVE LOGITS
     cancellation
    0.87
     Stornier
    0.83
     refunds
    0.81
     refund
    0.80
     Cancellation
    0.79
     cancellations
    0.78
    enumi
    0.76
     Refunds
    0.76
    Refunds
    0.75
    DataAnnotations
    0.74
    Act Density 0.395%

    No Known Activations