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

    Neuronpedia

    INDEX
    Explanations

    strings related to user profiles and forum posts

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or emotive expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
     nomine
    -0.74
     calendars
    -0.73
     Hust
    -0.71
     yearly
    -0.71
    awaru
    -0.68
     Twain
    -0.66
     dotted
    -0.65
     escaping
    -0.65
     enriched
    -0.64
    POSITIVE LOGITS
    Reply
    1.04
    lol
    0.98
    Posted
    0.93
    https
    0.90
    Spoiler
    0.88
    http
    0.85
    EDIT
    0.83
    Posts
    0.83
    ________________
    0.82
    Thread
    0.82
    Act Density 0.156%

    No Known Activations