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

    Neuronpedia

    INDEX
    Explanations

    ingredients and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and components related to food and cooking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.82
    PDATE
    -0.82
     Spiel
    -0.78
    Student
    -0.75
    ¥ŀ
    -0.74
    POST
    -0.74
     behavi
    -0.73
    Offline
    -0.73
    anooga
    -0.73
    ospace
    -0.71
    POSITIVE LOGITS
     berries
    1.13
     flakes
    1.10
    fruit
    1.06
     seeds
    1.04
     jelly
    0.98
    seed
    0.98
    bush
    0.95
     fungus
    0.94
     pulp
    0.92
     bushes
    0.92
    Act Density 0.191%

    No Known Activations