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

    Neuronpedia

    INDEX
    Explanations

    instances and variations of the word "do" in various contexts

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

    Follows "do" (verb)

    np_acts-logits-general · gemini-2.0-flash

    doomsday, do NOT, doggie, docket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.65
    GOTREF
    -0.64
    Skocz
    -0.63
    </tfoot>
    -0.62
    fold
    -0.62
    pushFollow
    -0.60
    期刊论文
    -0.59
     indisponible
    -0.59
    URLException
    -0.59
    httphttps
    -0.58
    POSITIVE LOGITS
    omsday
    0.59
     NOT
    0.58
     not
    0.58
     Nothing
    0.54
     nothing
    0.53
    Nothing
    0.52
    deca
    0.50
    nothing
    0.50
    metic
    0.49
    MessageOf
    0.49
    Act Density 0.071%

    No Known Activations