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

    Neuronpedia

    INDEX
    Explanations

    mentions of ingredients or steps in a recipe that involve chopping

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "chopped" and its variations in cooking contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ports
    -0.76
    forcing
    -0.73
    porting
    -0.73
    isle
    -0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.71
    Grey
    -0.68
    ships
    -0.68
     Gutenberg
    -0.66
    SPONSORED
    -0.66
    VERTIS
    -0.66
    POSITIVE LOGITS
     chop
    1.17
     Chop
    0.94
     onions
    0.93
     chunks
    0.92
     chops
    0.90
     slices
    0.89
    aneous
    0.89
    sticks
    0.88
     onion
    0.85
     chopping
    0.83
    Act Density 0.020%

    No Known Activations