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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or positive emotions

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

    "happy" preceding various nouns/events

    np_acts-logits-general · gemini-2.0-flash

    happy greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vrons
    -0.57
    HeaderText
    -0.55
    PageRoute
    -0.53
    :///
    -0.52
     Gaulle
    -0.51
    DataAnnotations
    -0.50
     Tuchel
    -0.50
    ként
    -0.48
    ://"
    -0.48
     perchance
    -0.48
    POSITIVE LOGITS
    HAPPY
    1.03
     happy
    1.01
     HAPPY
    0.97
    happy
    0.93
     Happy
    0.93
     happier
    0.92
     Felic
    0.91
    Happy
    0.87
     feliz
    0.86
     felizes
    0.84
    Act Density 0.079%

    No Known Activations