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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advertisements

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.64
     peanuts
    -0.58
    quartered
    -0.56
    ignt
    -0.53
     perspect
    -0.52
     nuts
    -0.51
    wives
    -0.51
     cherry
    -0.51
     overboard
    -0.50
     coerc
    -0.50
    POSITIVE LOGITS
    },"
    0.72
     ..........
    0.72
     advertisement
    0.69
     }
    0.69
     }}
    0.67
    advertisement
    0.65
     ]
    0.64
     Crossref
    0.64
    Story
    0.63
    <|endoftext|>
    0.63
    Act Density 0.014%

    No Known Activations