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

    Neuronpedia

    INDEX
    Explanations

    mentions and references to Twitter and its functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.82
    modelBuilder
    -0.76
     gainera
    -0.69
    WebVitals
    -0.67
    komen
    -0.67
     CTS
    -0.66
     useRef
    -0.66
     Koz
    -0.64
    Gor
    -0.63
    oa̍t
    -0.63
    POSITIVE LOGITS
     Twitter
    1.60
     tweets
    1.59
     tweet
    1.44
     Tweets
    1.43
     TWITTER
    1.41
     tweeting
    1.40
    Twitter
    1.38
     twitter
    1.34
     tweeted
    1.30
    TWITTER
    1.26
    Act Density 0.129%

    No Known Activations