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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "hour" and references to social gatherings or events involving food

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

    happy hours and named hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clothes
    -0.49
    ExtendWith
    -0.49
     createState
    -0.49
    Parcelize
    -0.48
     clothing
    -0.47
     HTMLElement
    -0.46
     Svg
    -0.46
     unknownFields
    -0.45
     useRef
    -0.45
     Clothes
    -0.45
    POSITIVE LOGITS
    Hour
    0.57
     Hour
    0.57
     HOUR
    0.55
    Lunch
    0.55
    lunch
    0.53
    hour
    0.52
     lunchtime
    0.52
     hour
    0.49
    ulemon
    0.48
    HOUR
    0.46
    Act Density 0.003%

    No Known Activations