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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and thankfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utnik
    -0.72
    lichung
    -0.67
    imageURL
    -0.59
    ftest
    -0.56
    iels
    -0.56
    ApiModel
    -0.55
     وتسجيلات
    -0.54
    &__
    -0.54
    testen
    -0.53
    voj
    -0.52
    POSITIVE LOGITS
     gratitude
    1.59
     thanking
    1.58
     thankful
    1.57
     grateful
    1.55
     thank
    1.36
     Gratitude
    1.35
    thank
    1.34
     thanked
    1.32
     THANK
    1.24
    rateful
    1.23
    Act Density 0.096%

    No Known Activations