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

    Neuronpedia

    INDEX
    Explanations

    interactions focused on compliments and expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     createState
    -0.49
    Климат
    -0.48
     Ahor
    -0.44
    UserScript
    -0.43
     Signalez
    -0.42
    XmlAccessorType
    -0.41
     sartén
    -0.40
     schie
    -0.40
     ahor
    -0.40
    ніципа
    -0.39
    POSITIVE LOGITS
     greeting
    0.71
     greetings
    0.70
    greeting
    0.60
     compliments
    0.59
     congrat
    0.59
    Greeting
    0.59
    REET
    0.59
     congratulated
    0.58
     greet
    0.57
     admiration
    0.57
    Act Density 0.164%

    No Known Activations