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

    Neuronpedia

    INDEX
    Explanations

    advertisements within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "advertisement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iland
    -0.75
    come
    -0.72
    ighed
    -0.72
    ologically
    -0.71
    ited
    -0.69
    adows
    -0.69
    cible
    -0.68
    ologic
    -0.67
    cil
    -0.66
    jer
    -0.66
    POSITIVE LOGITS
     Advertisement
    1.01
     advertisement
    0.97
     Thumbnails
    0.81
    Interstitial
    0.77
    vertising
    0.75
     Transcript
    0.75
    culosis
    0.72
    eering
    0.72
    ļéĨĴ
    0.71
     advertisements
    0.71
    Act Density 0.007%

    No Known Activations