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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.73
     Construct
    -0.72
     Osc
    -0.66
    FO
    -0.66
     Loft
    -0.65
    wide
    -0.62
    destruct
    -0.62
     Fires
    -0.62
    mouth
    -0.61
     Ultron
    -0.61
    POSITIVE LOGITS
     thank
    0.94
    giving
    0.89
     acknowled
    0.84
    gements
    0.83
     thanking
    0.83
    ĸļ
    0.81
    ingle
    0.79
    bly
    0.77
    ESCO
    0.77
    gments
    0.77
    Act Density 0.014%

    No Known Activations