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 and thankfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opers
    -0.74
    okin
    -0.74
    oto
    -0.67
    opped
    -0.63
    change
    -0.62
    uve
    -0.62
    uter
    -0.62
    agate
    -0.61
    quer
    -0.60
    bill
    -0.60
    POSITIVE LOGITS
    giving
    1.22
    fulness
    0.88
    ctuary
    0.85
     acknowled
    0.84
     citiz
    0.82
    gements
    0.80
     deity
    0.80
     God
    0.79
    gments
    0.78
     pardon
    0.78
    Act Density 0.042%

    No Known Activations