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

    Neuronpedia

    INDEX
    Explanations

    ingredients and cooking instructions in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and cooking-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \">
    -0.63
    åŃ
    -0.60
     Buckingham
    -0.59
     headlined
    -0.59
    ãĤª
    -0.58
     ironic
    -0.58
     AUTH
    -0.56
    ãĥĩ
    -0.54
     Schne
    -0.54
    udicrous
    -0.54
    POSITIVE LOGITS
     mixture
    1.45
     evenly
    0.95
     halves
    0.94
     ingredients
    0.92
     paste
    0.86
     cubes
    0.84
     gently
    0.82
     tablespoon
    0.81
    ixture
    0.81
     flakes
    0.80
    Act Density 0.081%

    No Known Activations