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

    Neuronpedia

    INDEX
    Explanations

    assertions or statements of importance and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loom
    -0.15
     Skull
    -0.15
    ascal
    -0.15
     gee
    -0.14
     flash
    -0.14
    fce
    -0.14
    cac
    -0.14
     barg
    -0.14
    ummy
    -0.14
    PG
    -0.14
    POSITIVE LOGITS
    unos
    0.15
    ourt
    0.14
     Ernest
    0.14
    /engine
    0.14
    à¸Ľà¸£à¸°à¸ª
    0.14
    WISE
    0.14
    TEM
    0.14
     nature
    0.14
     Fauc
    0.14
     faucet
    0.13
    Act Density 0.303%

    No Known Activations