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

    Neuronpedia

    INDEX
    Explanations

    references to food and drinks, particularly in relation to comfort and indulgence

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

    Follows "a" and precedes a drink container or food

    np_acts-logits-general · gemini-2.0-flash

    drink containers or portions after "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.63
    KommentareTeilen
    -0.56
     mairie
    -0.52
     intptr
    -0.51
    +:+
    -0.50
    abestanden
    -0.50
    flink
    -0.48
    XmlAccessorType
    -0.48
    ulares
    -0.48
    ifikationer
    -0.46
    POSITIVE LOGITS
     cup
    1.20
     glass
    1.18
     bowl
    1.13
     bottle
    1.12
     cups
    0.99
     pint
    0.96
     spoonful
    0.95
     dose
    0.94
    glass
    0.93
     slice
    0.87
    Act Density 0.233%

    No Known Activations