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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past tense verbs/adjectives of feeling

    np_acts-logits-general · gemini-2.0-flash

    feeling states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.44
     gé
    -0.38
     }{@
    -0.38
    */].
    -0.38
    MessageTagHelper
    -0.36
    بوابة
    -0.35
    责任编辑
    -0.35
     RDA
    -0.35
     hair
    -0.35
     Wikiseite
    -0.35
    POSITIVE LOGITS
     thrilled
    0.74
     Excited
    0.73
     delighted
    0.72
     pleased
    0.72
     excited
    0.69
    Excited
    0.66
     shocked
    0.66
     amazed
    0.64
     surprised
    0.63
     disappointed
    0.62
    Act Density 0.293%

    No Known Activations