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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and recognition for services rendered

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ุà¹ī
    -0.17
    éĽĦ
    -0.16
    580
    -0.14
     selling
    -0.14
    579
    -0.14
    627
    -0.14
    404
    -0.14
    ourd
    -0.14
    й
    -0.14
     Hope
    -0.14
    POSITIVE LOGITS
     reward
    0.45
     Reward
    0.36
     rewards
    0.36
    reward
    0.35
     appreciation
    0.34
     thank
    0.33
     gratitude
    0.33
     thanking
    0.31
     Rewards
    0.30
    Reward
    0.30
    Act Density 0.196%

    No Known Activations