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 thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.80
     Osc
    -0.69
     projecting
    -0.67
     Ukrain
    -0.67
     projected
    -0.66
    Dest
    -0.63
     Samoa
    -0.62
    objects
    -0.61
    ago
    -0.61
    destruct
    -0.60
    POSITIVE LOGITS
    giving
    1.42
     Thanks
    0.88
    gements
    0.86
     Credits
    0.86
    SG
    0.81
    Thanks
    0.79
    bye
    0.78
     Guys
    0.77
    brance
    0.77
     pardon
    0.75
    Act Density 0.018%

    No Known Activations