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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment in a text

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

    would like to thank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nloa
    -0.41
     CreateTagHelper
    -0.38
     Commencez
    -0.37
    IGENCE
    -0.35
     Efq
    -0.35
    タ
    -0.35
     internetowa
    -0.35
    関連記事
    -0.34
    lables
    -0.34
     mist
    -0.33
    POSITIVE LOGITS
     antemano
    0.67
     remercie
    0.63
     remercier
    0.56
     agradecimiento
    0.56
    Agrade
    0.54
     teşekkür
    0.52
     thank
    0.52
     thanking
    0.51
    ขอบคุณ
    0.51
     Construcción
    0.50
    Act Density 0.057%

    No Known Activations