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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oplasty
    -0.58
    liesslich
    -0.58
    udadera
    -0.54
    acrylamide
    -0.54
    Czytaj
    -0.52
     NDEBUG
    -0.52
    tegra
    -0.52
     subscript
    -0.52
    Hebrews
    -0.51
    ⚧
    -0.51
    POSITIVE LOGITS
    That
    1.28
     That
    1.14
    THAT
    1.03
    that
    1.02
    Thats
    0.87
     THAT
    0.86
    那
    0.84
    thats
    0.83
     Thats
    0.83
     thats
    0.72
    Act Density 0.158%

    No Known Activations