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

    Neuronpedia

    INDEX
    Explanations

    verification tasks, specifically looking for the action of clicking on a box to verify not being a robot

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to verification steps or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.78
    ibaba
    -0.76
    gow
    -0.70
    ensional
    -0.70
    Reply
    -0.68
    ynchronous
    -0.66
    etsk
    -0.65
    pmwiki
    -0.65
    ovember
    -0.63
    sein
    -0.61
    POSITIVE LOGITS
     clicking
    0.81
    unct
    0.73
    product
    0.72
    products
    0.71
     mistake
    0.70
     annotation
    0.65
     subscribing
    0.65
    ãĤ®
    0.63
    éĥ
    0.61
     virtue
    0.61
    Act Density 0.017%

    No Known Activations