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

    Neuronpedia

    INDEX
    Explanations

    hashtags in text data

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hashtags on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tos
    -0.65
     Aberdeen
    -0.63
     Tests
    -0.63
    �
    -0.63
     Overse
    -0.62
     Payne
    -0.62
     Init
    -0.59
     ER
    -0.59
     Petersen
    -0.59
     Clear
    -0.58
    POSITIVE LOGITS
     hashtag
    3.89
     hasht
    2.78
     tweet
    1.58
     retweet
    1.56
     slogan
    1.47
     tweets
    1.32
     tweeting
    1.32
     emoji
    1.29
     "#
    1.28
     twitter
    1.27
    Act Density 0.018%

    No Known Activations