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

    Neuronpedia

    INDEX
    Explanations

    references to Twitter and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemGroup
    -0.68
    ArgsConstructor
    -0.67
     Kelle
    -0.63
    makeConstraints
    -0.62
     Koz
    -0.61
     Gardner
    -0.61
     ostavi
    -0.61
    orElseThrow
    -0.61
    providedIn
    -0.61
    modelBuilder
    -0.61
    POSITIVE LOGITS
     tweets
    1.79
     Twitter
    1.77
     Tweets
    1.63
     tweet
    1.62
     TWITTER
    1.56
     twitter
    1.54
     tweeting
    1.52
    Twitter
    1.51
     tweeted
    1.48
    weeted
    1.40
    Act Density 0.078%

    No Known Activations