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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensement
    -0.52
    ustimmung
    -0.51
     transfieras
    -0.50
    ukunft
    -0.45
    ArrowToggle
    -0.44
    LabelTagHelper
    -0.43
    ftagPool
    -0.42
    PullParser
    -0.42
     Walkover
    -0.42
    下一篇
    -0.41
    POSITIVE LOGITS
    GEBURTS
    0.72
     thanked
    0.71
     gratitude
    0.70
     thanking
    0.66
     grateful
    0.65
    ветить
    0.65
     thankful
    0.65
     tqdm
    0.64
     gratefully
    0.64
     appreciated
    0.64
    Act Density 0.195%

    No Known Activations