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

    Neuronpedia

    INDEX
    Explanations

    specific text indicating advertisements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of advertisements or references to advertisements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     determination
    -0.61
    ĪĴ
    -0.61
    alist
    -0.57
     statistical
    -0.55
     awakening
    -0.53
     measurement
    -0.52
     tal
    -0.52
     accommodation
    -0.52
     deduct
    -0.51
     representative
    -0.51
    POSITIVE LOGITS
    advertisement
    0.77
     Continue
    0.74
    embed
    0.67
     CONTIN
    0.66
    RELATED
    0.62
     Cancel
    0.62
    é¾įå
    0.61
     VIDEOS
    0.61
     Expand
    0.61
     Advertisement
    0.59
    Act Density 0.029%

    No Known Activations