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

    Neuronpedia

    INDEX
    Explanations

    dialogue or quotes within a story

    oai_token-act-pair · gpt-3.5-turbo

    conversational elements and direct speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.74
    CONCLUS
    -0.63
    EU
    -0.62
     Cosponsors
    -0.62
    Indeed
    -0.61
    Firstly
    -0.61
    UGC
    -0.59
    Furthermore
    -0.59
    agonists
    -0.58
    untled
    -0.58
    POSITIVE LOGITS
     âĢ¦"
    1.33
     ..."
    1.21
    ,'"
    1.20
    "—
    1.14
    !'"
    1.12
    .")
    1.11
    ,"
    1.10
    ?"
    1.09
    ?'"
    1.08
    !"
    1.07
    Act Density 0.925%

    No Known Activations