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

    Neuronpedia

    INDEX
    Explanations

    references to dictionaries or similar data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pportun
    -0.69
    ngdoc
    -0.68
    ophys
    -0.62
    afterEach
    -0.61
    Бахар
    -0.61
    tshell
    -0.60
    lesia
    -0.58
    ítě
    -0.57
     Fland
    -0.57
    RSpec
    -0.55
    POSITIVE LOGITS
    Dict
    1.18
     dictionary
    1.11
    Dictionary
    1.09
     Dictionary
    1.05
     Dict
    0.99
     dictionaries
    0.99
    dict
    0.97
     dict
    0.95
    dictionary
    0.93
    字典
    0.90
    Act Density 0.110%

    No Known Activations