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

    Neuronpedia

    INDEX
    Explanations

    terms related to social media algorithms and user interaction features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webs
    -0.15
     stereotypes
    -0.14
    ulary
    -0.14
    obao
    -0.14
     Moff
    -0.14
     Websites
    -0.14
     specular
    -0.14
    mpar
    -0.14
    905
    -0.13
     TK
    -0.13
    POSITIVE LOGITS
     feed
    0.25
     wall
    0.23
     timeline
    0.22
     Feed
    0.21
    feed
    0.21
    timeline
    0.21
     Wall
    0.21
    -feed
    0.20
    wall
    0.19
     Timeline
    0.19
    Act Density 0.114%

    No Known Activations