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

    Neuronpedia

    INDEX
    Explanations

    descriptions and qualities of different types of tea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pizza
    -0.17
     hamburger
    -0.15
     Pizza
    -0.15
     Pasta
    -0.15
    tom
    -0.14
    pizza
    -0.14
     Meat
    -0.14
    ält
    -0.13
    icana
    -0.13
    okie
    -0.13
    POSITIVE LOGITS
     tea
    0.56
     Tea
    0.48
     teas
    0.48
    tea
    0.42
    èĮ¶
    0.39
    Te
    0.36
    -te
    0.35
     Te
    0.35
     te
    0.35
     TE
    0.35
    Act Density 0.106%

    No Known Activations