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 or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.87
    uclear
    -0.72
    arist
    -0.67
    objects
    -0.67
     Osc
    -0.65
    åĬ
    -0.62
    spir
    -0.62
     projected
    -0.61
    ago
    -0.61
    iche
    -0.61
    POSITIVE LOGITS
    giving
    1.41
     GOODMAN
    0.80
    haw
    0.80
     Guys
    0.79
    gements
    0.78
     Thanks
    0.78
     pardon
    0.76
     Credits
    0.75
    bye
    0.74
    brance
    0.72
    Act Density 0.016%

    No Known Activations