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

    Neuronpedia

    INDEX
    Explanations

    words related to online content linking to related articles or stories

    oai_token-act-pair · gpt-3.5-turbo

    signals that indicate the presence of related content or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.79
    ainted
    -0.76
    UGE
    -0.72
    omething
    -0.70
    Ĥİ
    -0.69
    aper
    -0.69
    esan
    -0.69
    anut
    -0.65
    elfth
    -0.63
     clad
    -0.63
    POSITIVE LOGITS
     Stories
    1.16
     Content
    1.07
     Links
    1.03
     Articles
    0.95
     ARTICLE
    0.90
     Posts
    0.89
     Topics
    0.89
     Video
    0.85
     articles
    0.85
     VIDEOS
    0.84
    Act Density 0.026%

    No Known Activations