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

    Neuronpedia

    INDEX
    Explanations

    references to Napoleon and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emente
    -0.17
    iams
    -0.15
    .handleClick
    -0.15
    OUNDS
    -0.14
    PACK
    -0.14
    iquement
    -0.14
    ï¸
    -0.14
    issen
    -0.14
    orida
    -0.14
    ngr
    -0.14
    POSITIVE LOGITS
     Nap
    0.28
    oleon
    0.27
     nap
    0.23
    alm
    0.22
    uns
    0.20
    erville
    0.20
    flix
    0.20
    kin
    0.20
    kins
    0.18
    ster
    0.18
    Act Density 0.007%

    No Known Activations