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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Default
    -0.69
    conserv
    -0.61
    soDeliveryDate
    -0.61
    estyles
    -0.61
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
     destructive
    -0.59
    Ranked
    -0.59
     weeds
    -0.58
    estyle
    -0.58
     Fires
    -0.56
    POSITIVE LOGITS
     gracious
    0.92
     thank
    0.84
     kindly
    0.80
     blessings
    0.79
     congratulations
    0.79
     goodbye
    0.79
     Thank
    0.78
     sir
    0.78
    animous
    0.77
     sacrific
    0.76
    Act Density 0.096%

    No Known Activations