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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or thankfulness

    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
    女
    -0.78
     Samoa
    -0.73
    ago
    -0.72
     Hurricanes
    -0.71
     Ultron
    -0.68
     diver
    -0.63
    spir
    -0.61
     detached
    -0.60
     Luxem
    -0.60
     inhabited
    -0.59
    POSITIVE LOGITS
    giving
    1.22
     Thanks
    1.00
    bye
    0.90
     Credits
    0.84
    Thanks
    0.84
    udos
    0.79
     Guys
    0.78
     thanks
    0.77
     pardon
    0.75
    reenshots
    0.74
    Act Density 0.010%

    No Known Activations