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

    Neuronpedia

    INDEX
    Explanations

    references to online engagement and social media interaction

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

    Twitter and social media

    np_acts-logits-general · gemini-2.0-flash

    Twitter and social media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Funktions
    -0.53
     klasse
    -0.52
     Vorstellungen
    -0.51
    hoben
    -0.50
     Lengkap
    -0.48
    ondheim
    -0.47
     tranquille
    -0.46
    matite
    -0.46
    ValueStyle
    -0.46
     stripe
    -0.45
    POSITIVE LOGITS
     Twitter
    1.69
     tweets
    1.53
     twitter
    1.44
     hashtag
    1.44
     tweet
    1.43
    Twitter
    1.41
     Tweets
    1.39
     tweeting
    1.39
     social
    1.29
     hashtags
    1.28
    Act Density 0.260%

    No Known Activations