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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gratitude and recognition

    oai_token-act-pair · gpt-3.5-turbo

    instances of expressions of gratitude or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arist
    -0.87
    OPER
    -0.71
    emate
    -0.71
    negie
    -0.69
    cas
    -0.69
    vent
    -0.67
    andro
    -0.67
    atorial
    -0.65
    amus
    -0.65
    omaly
    -0.65
    POSITIVE LOGITS
     thanked
    1.19
     thanking
    1.08
     goodbye
    0.79
    wana
    0.78
    nesday
    0.75
    hello
    0.75
     praised
    0.74
     applauded
    0.72
    ifully
    0.71
     hello
    0.70
    Act Density 0.007%

    No Known Activations