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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "do" in various tenses and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odus
    -0.16
    rei
    -0.14
    tright
    -0.14
    ati
    -0.14
    ford
    -0.14
    é
    -0.14
    ulo
    -0.14
    angi
    -0.14
    rans
    -0.14
    amento
    -0.14
    POSITIVE LOGITS
     when
    0.18
    elen
    0.16
    ÙĨدÙĩ
    0.15
    /do
    0.15
    CORE
    0.14
     Poh
    0.14
     throughout
    0.14
    ITS
    0.14
     khi
    0.14
    ones
    0.14
    Act Density 0.044%

    No Known Activations