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

    Neuronpedia

    INDEX
    Explanations

    the word "to" and its various forms and usages in the text.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARE
    -0.15
    owie
    -0.15
    æĥł
    -0.14
    ctic
    -0.14
     Fur
    -0.14
    inar
    -0.13
    ân
    -0.13
    RelativeTo
    -0.13
    acks
    -0.13
    ynos
    -0.13
    POSITIVE LOGITS
    ienes
    0.15
     associate
    0.15
     Associate
    0.15
    rones
    0.15
    ocache
    0.14
    frage
    0.14
     Vladim
    0.14
    uong
    0.14
    gens
    0.14
    unya
    0.14
    Act Density 0.112%

    No Known Activations