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

    Neuronpedia

    INDEX
    Explanations

    phrases related to drinking and containers such as cups and jars

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to drinking and consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     invari
    -0.70
     architecture
    -0.70
     canonical
    -0.69
     arche
    -0.68
     backward
    -0.66
     incumb
    -0.66
     symmetry
    -0.65
    ĺħ
    -0.65
     graceful
    -0.64
     pioneer
    -0.63
    POSITIVE LOGITS
     bottles
    1.42
     bottle
    1.29
     cans
    1.10
    cohol
    1.02
     liquor
    1.00
     soda
    0.99
    Cola
    0.99
     cig
    0.98
     whiskey
    0.96
     vodka
    0.95
    Act Density 0.291%

    No Known Activations