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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.70
     autorytatywna
    -0.51
     protoimpl
    -0.42
     שוליים
    -0.41
     виправивши
    -0.41
    IsContent
    -0.40
    SourceChecksum
    -0.39
     وتسجيلات
    -0.39
     caractères
    -0.38
    ագրություններ
    -0.36
    POSITIVE LOGITS
     thanking
    0.80
    ขอบคุณ
    0.77
     thanked
    0.76
    Agrade
    0.72
    Dziękuję
    0.71
     thank
    0.70
     remercie
    0.70
     remercier
    0.68
    thank
    0.67
     agradecer
    0.66
    Act Density 0.160%

    No Known Activations