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

    Neuronpedia

    INDEX
    Explanations

    instructions or steps for baking or cooking

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions or recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )."
    -0.53
    ).[
    -0.50
    ]."
    -0.47
    %).
    -0.45
    .).
    -0.44
    .</
    -0.43
    ."[
    -0.42
    ").
    -0.42
    ).
    -0.42
    !).
    -0.41
    POSITIVE LOGITS
     FANTASY
    0.40
    ENTS
    0.33
     Tags
    0.32
    anchester
    0.32
     Bib
    0.31
     Canaver
    0.31
     Anthrop
    0.31
     Hallow
    0.31
    ':
    0.30
    cients
    0.30
    Act Density 4.126%

    No Known Activations