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

    Neuronpedia

    INDEX
    Explanations

    the word "Deep" and its variations, indicating a focus on depth-related concepts or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acob
    -0.17
    .scalablytyped
    -0.17
    BOARD
    -0.15
    ÑħÑĥ
    -0.15
    ynchronized
    -0.15
    Äħd
    -0.14
    eyer
    -0.14
    pic
    -0.14
    ous
    -0.14
    aggio
    -0.14
    POSITIVE LOGITS
    ening
    0.24
    dish
    0.20
    (er
    0.19
     Dish
    0.19
    fake
    0.18
    ly
    0.18
     dish
    0.18
    fried
    0.18
     Elem
    0.18
    ak
    0.17
    Act Density 0.011%

    No Known Activations