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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Wag" or related concepts

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

    Wag, Wagria, Wagener, Wagner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ITT
    -0.55
    jsii
    -0.53
    prefixer
    -0.52
    anii
    -0.50
     Fontana
    -0.50
    Portale
    -0.49
    DRE
    -0.48
    III
    -0.48
    Ii
    -0.47
    CCR
    -0.47
    POSITIVE LOGITS
     Wag
    2.23
    Wag
    2.17
     wag
    2.11
    wag
    1.95
     WAG
    1.52
     wagons
    1.09
     Wagon
    1.04
     wagon
    1.03
    Wagon
    0.93
     Wagner
    0.91
    Act Density 0.003%

    No Known Activations