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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "tweet"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tweet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.61
    iHUD
    -0.61
     Sind
    -0.59
     Defin
    -0.59
     Prest
    -0.58
    iencies
    -0.58
    vantage
    -0.58
     circumcised
    -0.57
     certs
    -0.57
    ately
    -0.57
    POSITIVE LOGITS
    storm
    1.42
    storms
    1.40
     "@
    0.97
    deck
    0.94
     retweet
    0.94
    weet
    0.90
    Tweet
    0.84
     hasht
    0.84
     hashtag
    0.82
    realDonaldTrump
    0.81
    Act Density 0.037%

    No Known Activations