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

    Neuronpedia

    INDEX
    Explanations

    keywords related to community governance and moderation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Moderation-related terms and discussion

    np_acts-logits-general · gemini-2.0-flash

    moderator actions and duties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.60
     EconPapers
    -0.50
    principalTable
    -0.50
    webElementGuid
    -0.48
    MessageOf
    -0.47
    تقاوى
    -0.46
     незавершена
    -0.46
    styleType
    -0.45
    ANDUM
    -0.43
     OMIT
    -0.43
    POSITIVE LOGITS
     newbies
    0.48
     screenshots
    0.46
     pomeriggio
    0.45
    astify
    0.45
     newbie
    0.44
     screenshot
    0.44
     spamming
    0.43
     politeness
    0.43
     moderators
    0.43
     kittens
    0.42
    Act Density 0.428%

    No Known Activations