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

    Neuronpedia

    INDEX
    Explanations

    key elements indicating significance, improvement, or community connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elper
    -0.15
     revealing
    -0.14
    Shield
    -0.14
     Wikip
    -0.13
    iversit
    -0.13
    kup
    -0.13
    iên
    -0.13
    setDefault
    -0.13
    aw
    -0.13
    hammad
    -0.13
    POSITIVE LOGITS
     evidence
    0.34
     proof
    0.31
     demonstration
    0.30
     symbol
    0.29
     Evidence
    0.28
    symbol
    0.27
     evid
    0.26
     indication
    0.26
    Demon
    0.26
    -symbol
    0.26
    Act Density 0.018%

    No Known Activations