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
    omik
    -0.14
    enberg
    -0.14
    ellar
    -0.14
     Mei
    -0.14
     THAT
    -0.14
    ãĥ¼ãĥIJ
    -0.14
    sm
    -0.13
    éĤ£ä¹Ī
    -0.13
    tron
    -0.13
    mong
    -0.13
    POSITIVE LOGITS
     of
    0.24
     của
    0.23
    cher
    0.20
    bedo
    0.19
     ones
    0.17
    zelf
    0.17
    ffer
    0.16
    ÃĹ↵↵
    0.16
    OfFile
    0.15
    jen
    0.14
    Act Density 0.043%

    No Known Activations