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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tomato"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tomato" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.90
    rams
    -0.85
    draw
    -0.75
    nces
    -0.74
    ledged
    -0.72
    trak
    -0.71
    pter
    -0.71
    olulu
    -0.71
    tml
    -0.71
    mable
    -0.71
    POSITIVE LOGITS
     tomatoes
    0.99
     tomato
    0.98
     juice
    0.90
    fruit
    0.90
    grass
    0.85
     plants
    0.83
    atoes
    0.82
     harvest
    0.81
    iculture
    0.80
     vegetables
    0.78
    Act Density 0.011%

    No Known Activations