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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "draw" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clair
    -0.19
    adece
    -0.15
    ngr
    -0.15
    виÑī
    -0.15
    ipop
    -0.15
    LIKELY
    -0.15
    nÃŃ
    -0.14
    readcr
    -0.14
    elho
    -0.14
    UDGE
    -0.14
    POSITIVE LOGITS
    esome
    0.17
    backs
    0.17
     attention
    0.15
    orld
    0.15
    itness
    0.14
    ÙĨدÙĩ
    0.14
    tight
    0.14
    pull
    0.14
     drawn
    0.14
     meisten
    0.14
    Act Density 0.046%

    No Known Activations