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

    Neuronpedia

    INDEX
    Explanations

    references to data structures used in programming, particularly dictionaries

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

    dictionary and dictionary-like data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itemView
    -0.34
    即
    -0.33
    want
    -0.32
    TestId
    -0.32
    甲
    -0.30
    Bali
    -0.29
    可是
    -0.29
    save
    -0.29
    malen
    -0.28
    rospy
    -0.28
    POSITIVE LOGITS
     Dictionary
    2.47
    Dictionary
    2.28
     dictionary
    1.75
     DICTION
    1.54
     dictionaries
    1.52
     Dictionaries
    1.42
    dictionary
    1.40
    ictionary
    1.31
    Diction
    1.30
     diccionario
    1.16
    Act Density 0.002%

    No Known Activations