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

    Neuronpedia

    INDEX
    Explanations

    references to soups made from fresh or local ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ift
    -0.17
    isz
    -0.16
     Landing
    -0.15
     âĹĦ
    -0.15
     landing
    -0.15
    áze
    -0.15
    iry
    -0.14
    lobal
    -0.14
    ewidth
    -0.14
    landing
    -0.14
    POSITIVE LOGITS
     soup
    0.30
     Soup
    0.29
     broth
    0.27
    soup
    0.22
    湯
    0.22
     simmer
    0.21
    Soup
    0.20
    æ±
    0.19
    uppe
    0.19
    oup
    0.18
    Act Density 0.033%

    No Known Activations