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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of discussions or interactions in online forums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iale
    -0.16
    åĩºçīĪ
    -0.15
     Whatsapp
    -0.15
    Slides
    -0.14
     пеÑĢел
    -0.14
    -instagram
    -0.14
    undles
    -0.14
    inaire
    -0.13
    auses
    -0.13
    Tweet
    -0.13
    POSITIVE LOGITS
     thread
    0.53
     threads
    0.49
     Thread
    0.48
    thread
    0.44
    -thread
    0.42
     forum
    0.40
    Thread
    0.40
     Threads
    0.40
     THREAD
    0.39
    threads
    0.38
    Act Density 0.258%

    No Known Activations