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
     Hurricanes
    -0.77
     Samoa
    -0.66
     Chern
    -0.65
     Hera
    -0.65
     Ultron
    -0.64
     Islanders
    -0.63
     Ukrain
    -0.63
    Sham
    -0.63
     Loft
    -0.62
     Ain
    -0.62
    POSITIVE LOGITS
    giving
    1.11
     thanks
    1.01
    ĸļ
    0.98
    gment
    0.87
     Thanks
    0.86
    esson
    0.86
    udos
    0.83
     congratulations
    0.83
    awaru
    0.81
    creen
    0.78
    Act Density 0.011%

    No Known Activations