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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the word "comments" in comments sections

    oai_token-act-pair · gpt-3.5-turbo

    references to interacting in the comments section of a post

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ça
    -0.76
    neys
    -0.74
    ISM
    -0.73
     Reborn
    -0.72
     Rescue
    -0.71
    isen
    -0.70
     abduction
    -0.69
    ccording
    -0.69
     Vision
    -0.69
    facts
    -0.66
    POSITIVE LOGITS
     comments
    0.94
    ariat
    0.88
    comments
    0.85
    pring
    0.82
     comment
    0.81
     sections
    0.80
     commenters
    0.80
     threads
    0.79
     thread
    0.78
     posts
    0.78
    Act Density 0.034%

    No Known Activations