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

    Neuronpedia

    INDEX
    Explanations

    mentions and interactions on social media, specifically Twitter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    twitter mentions and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.55
    featureID
    -0.54
    LookAnd
    -0.46
    TagMode
    -0.46
    Становништво
    -0.45
    Aholisi
    -0.44
    ########.
    -0.43
     disponibilités
    -0.43
    Elő
    -0.42
    BeginInit
    -0.42
    POSITIVE LOGITS
    twimg
    0.81
     Twitter
    0.80
     tweet
    0.79
     tweeting
    0.75
     tweets
    0.75
     twitter
    0.74
     tweeted
    0.73
     Tweet
    0.72
     Tweets
    0.69
    Twitter
    0.61
    Act Density 0.123%

    No Known Activations