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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recipes or ingredient lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨÚ¯ÛĮ
    -0.16
    ãĥ³ãĥĨ
    -0.16
     vic
    -0.15
    gross
    -0.14
    onu
    -0.14
    minster
    -0.14
     hel
    -0.14
    ORIES
    -0.14
    manship
    -0.14
    zel
    -0.14
    POSITIVE LOGITS
     only
    0.20
     readily
    0.19
     materials
    0.19
     ingredients
    0.19
    materials
    0.18
     resources
    0.17
    itel
    0.16
     Only
    0.16
    only
    0.16
    deniz
    0.15
    Act Density 0.185%

    No Known Activations