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

    Neuronpedia

    INDEX
    Explanations

    special characters such as quotes and parentheses

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks or references to dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nieto
    -0.79
     offended
    -0.76
     Klu
    -0.73
     synd
    -0.72
     cancell
    -0.71
     predomin
    -0.71
     Tribune
    -0.70
     retribution
    -0.70
     anim
    -0.69
     constitu
    -0.69
    POSITIVE LOGITS
    normal
    1.11
    cheat
    1.11
    false
    1.08
    true
    1.08
    official
    1.06
    Hey
    1.04
    BuyableInstoreAndOnline
    1.02
    catentry
    1.02
    Hello
    1.01
    Empty
    1.01
    Act Density 0.108%

    No Known Activations