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

    Neuronpedia

    INDEX
    Explanations

    references to hot and warm temperatures, particularly in relation to food and beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.87
    ellschaft
    -0.81
     تانيه
    -0.78
    kegaard
    -0.77
     مرئيه
    -0.76
    granate
    -0.76
     Caballero
    -0.73
     للاسماء
    -0.72
    PreferredItem
    -0.72
    CloseOperation
    -0.72
    POSITIVE LOGITS
     Hot
    1.34
     hot
    1.23
     HOT
    1.23
    Hot
    1.23
    hot
    1.16
    HOT
    1.12
     hotter
    1.06
     chaud
    1.05
     temperatures
    1.01
     temperature
    0.99
    Act Density 0.106%

    No Known Activations