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

    Neuronpedia

    INDEX
    Explanations

    forum-related topics and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to online discussion forums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lys
    -0.70
    displayText
    -0.68
    efe
    -0.65
     Stevenson
    -0.64
     Lilly
    -0.62
     Kear
    -0.62
    EFF
    -0.62
    sea
    -0.61
    mson
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
     thread
    1.11
     forum
    1.04
     moderators
    1.04
     forums
    1.02
     threads
    1.01
     moderator
    0.99
     Forums
    0.97
    forum
    0.93
     postings
    0.92
     moder
    0.92
    Act Density 0.049%

    No Known Activations