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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.76
     damning
    -0.70
     contends
    -0.69
    ths
    -0.66
     warfare
    -0.65
    poses
    -0.64
     undesirable
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
     hostilities
    -0.62
     bruising
    -0.62
    POSITIVE LOGITS
    ortium
    0.87
    iets
    0.78
    RIP
    0.76
     Thank
    0.76
     generously
    0.75
     congr
    0.72
     THANK
    0.72
     sponsors
    0.72
    omever
    0.70
    Thank
    0.69
    Act Density 0.262%

    No Known Activations