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

    Neuronpedia

    INDEX
    Explanations

    confirmation messages and expressions of appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    thank you, congratulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tourists
    -0.35
     lenker
    -0.35
     zewnętrzne
    -0.33
     Touristen
    -0.31
     OGSÅ
    -0.31
    assero
    -0.31
     Tourists
    -0.31
    既
    -0.30
     scraps
    -0.30
    はもちろん
    -0.29
    POSITIVE LOGITS
    Congratulations
    0.97
     Congratulations
    0.96
     congratulations
    0.93
     congrats
    0.82
    congratulations
    0.82
     thank
    0.82
     Congrats
    0.81
    Congrats
    0.80
    Your
    0.79
     congratulate
    0.79
    Act Density 0.041%

    No Known Activations