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

    Neuronpedia

    INDEX
    Explanations

    descriptions of food and flavors

    oai_token-act-pair · gpt-3.5-turbo

    the word "delicious" and variations of its sentiment in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.70
    BU
    -0.69
     Dru
    -0.68
    Mesh
    -0.65
    mberg
    -0.64
     Huntington
    -0.64
    den
    -0.64
    vere
    -0.63
    patient
    -0.62
    FT
    -0.61
    POSITIVE LOGITS
     delicious
    1.40
     Delicious
    1.14
     tasty
    1.12
     juicy
    1.07
    nesses
    0.98
     nutritious
    0.97
     meals
    0.96
     pastry
    0.93
     tasting
    0.92
    ness
    0.92
    Act Density 0.009%

    No Known Activations