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

    Neuronpedia

    INDEX
    Explanations

    references to Twitter and its associated functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.61
     Portail
    -0.60
     disambiguazione
    -0.54
    cipar
    -0.53
     Roskov
    -0.52
    PropertyGroup
    -0.52
    Spoljašnje
    -0.52
     mouseY
    -0.51
    таратура
    -0.51
     online
    -0.50
    POSITIVE LOGITS
     tweet
    1.42
     Twitter
    1.41
     tweets
    1.39
     twitter
    1.34
     tweeting
    1.30
     tweeted
    1.29
     Tweet
    1.29
     Tweets
    1.28
    Twitter
    1.28
    Tweets
    1.26
    Act Density 0.106%

    No Known Activations