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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.76
    ccording
    -0.69
    JECT
    -0.66
    Temperature
    -0.65
    Downloadha
    -0.61
    Ranked
    -0.60
     Purg
    -0.60
    onde
    -0.60
    Pred
    -0.59
    amental
    -0.57
    POSITIVE LOGITS
     sacrific
    0.80
     kindly
    0.78
     Almighty
    0.74
     bravery
    0.73
     defer
    0.72
     blessings
    0.70
     generously
    0.69
    chal
    0.68
     kindness
    0.67
     generosity
    0.67
    Act Density 0.112%

    No Known Activations