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

    Neuronpedia

    INDEX
    Explanations

    mentions of various types of potatoes

    oai_token-act-pair · gpt-3.5-turbo

    references to "potato" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inances
    -0.82
    anwhile
    -0.81
    andem
    -0.79
    stract
    -0.79
    olulu
    -0.78
    eanor
    -0.75
    ovie
    -0.74
    eger
    -0.73
    lasses
    -0.71
    uilt
    -0.70
    POSITIVE LOGITS
     starch
    1.04
     potato
    1.00
    atoes
    0.97
     potatoes
    0.96
    assium
    0.96
     Potato
    0.90
    cake
    0.87
    weed
    0.85
     chips
    0.85
     salad
    0.84
    Act Density 0.006%

    No Known Activations