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

    Neuronpedia

    INDEX
    Explanations

    references to bottles, specifically in various contexts related to types and attributes of bottles

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

    bottle flips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ajax
    -0.60
     archbishop
    -0.60
     EconPapers
    -0.58
     voran
    -0.56
     Gabi
    -0.56
    Stacy
    -0.55
     Wildcats
    -0.54
     Majestic
    -0.54
    MARC
    -0.54
     Stacy
    -0.54
    POSITIVE LOGITS
     bottle
    2.27
     Bottle
    2.14
    Bottle
    2.06
    bottle
    2.06
     bottles
    1.80
     BOTT
    1.70
     Bottles
    1.70
     botella
    1.68
     bouteille
    1.56
    bottles
    1.54
    Act Density 0.003%

    No Known Activations