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

    Neuronpedia

    INDEX
    Explanations

    French words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to food and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Koreans
    -0.75
     Flake
    -0.72
     Rohingya
    -0.72
     Bulgarian
    -0.71
     Croatian
    -0.70
     Mariners
    -0.68
     Uzbek
    -0.67
     Ethiopian
    -0.66
     Reborn
    -0.66
     Adin
    -0.66
    POSITIVE LOGITS
     les
    1.38
     une
    1.32
     qui
    1.18
     Ãł
    1.17
     dé
    1.15
     pour
    1.14
     ré
    1.13
     vot
    1.10
     au
    1.09
     aux
    1.06
    Act Density 0.060%

    No Known Activations