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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "did."

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

    do not / did not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.60
    -0.51
     iParam
    -0.48
     дописавши
    -0.47
    Parcelize
    -0.47
    awtextra
    -0.46
    endregion
    -0.46
    writeFieldEnd
    -0.44
    ParseTree
    -0.44
    Viitteet
    -0.44
    POSITIVE LOGITS
     does
    0.62
     khong
    0.58
     not
    0.56
     không
    0.54
     tidak
    0.53
     neither
    0.51
    ulongan
    0.48
     geene
    0.48
     cannot
    0.48
     zoude
    0.47
    Act Density 0.076%

    No Known Activations