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

    Neuronpedia

    INDEX
    Explanations

    references to potatoes and related food terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Marco
    -0.16
     Marco
    -0.16
    adil
    -0.15
     Kra
    -0.15
    asin
    -0.15
    pw
    -0.15
    adel
    -0.15
    se
    -0.15
    adio
    -0.14
    CCC
    -0.14
    POSITIVE LOGITS
     potatoes
    0.35
     potato
    0.35
     Potato
    0.33
     tub
    0.26
     Idaho
    0.24
     Chips
    0.24
     fries
    0.24
     starch
    0.23
     chips
    0.23
    atoes
    0.22
    Act Density 0.016%

    No Known Activations