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

    Neuronpedia

    INDEX
    Explanations

    terms related to fried foods and cooking methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fried and roasted foods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exacts
    -0.44
    Życiorys
    -0.41
    ----</
    -0.41
    PUS
    -0.41
     Cred
    -0.40
    vud
    -0.39
     econom
    -0.39
     ngại
    -0.38
    itudes
    -0.38
     Mets
    -0.38
    POSITIVE LOGITS
     frying
    0.87
     roasting
    0.86
     roasted
    0.75
    roasted
    0.74
    RegressionTest
    0.73
    Roasted
    0.68
    Roast
    0.66
     Roasted
    0.65
     roast
    0.65
     fried
    0.64
    Act Density 0.016%

    No Known Activations