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

    Neuronpedia

    INDEX
    Explanations

    references to tea and its perceived benefits

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

    drinking tea

    np_acts-logits-general · gemini-2.0-flash

    drinking tea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ControllerBase
    -0.66
     الحره
    -0.57
     Phal
    -0.57
     propOrder
    -0.54
    ьаж
    -0.53
    DataAnnotations
    -0.53
     Rockefeller
    -0.52
     StatefulWidget
    -0.50
     phosphorylation
    -0.50
     Sony
    -0.49
    POSITIVE LOGITS
     tea
    2.31
     Tea
    2.00
    Tea
    1.90
    tea
    1.70
     TEA
    1.59
     teas
    1.58
     teapot
    1.43
    TEA
    1.40
     Teas
    1.36
    茶
    1.22
    Act Density 0.102%

    No Known Activations