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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "Napoleon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngr
    -0.18
    uckle
    -0.16
    PACK
    -0.15
    createClass
    -0.14
    OUNDS
    -0.14
    elay
    -0.14
    ensible
    -0.14
    issen
    -0.14
    egers
    -0.14
    597
    -0.14
    POSITIVE LOGITS
    oleon
    0.35
    olean
    0.26
    kins
    0.25
    erville
    0.25
    kin
    0.24
    olet
    0.24
    alm
    0.23
    ole
    0.23
    ier
    0.21
     Nap
    0.21
    Act Density 0.004%

    No Known Activations