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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or pair structures, particularly in data contexts

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

    key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ContentLoaded
    -0.52
    IGraphics
    -0.44
     Skelton
    -0.43
     Houghton
    -0.42
    Sch
    -0.42
    óa
    -0.39
     Sch
    -0.37
     Harwood
    -0.37
    tob
    -0.36
    Зем
    -0.36
    POSITIVE LOGITS
    Pair
    2.66
     Pair
    2.41
    pair
    2.05
     PAIR
    1.78
     pair
    1.78
    PAIR
    1.71
    Pairs
    1.45
     Pairs
    1.41
     paire
    1.37
     pairwise
    1.28
    Act Density 0.010%

    No Known Activations