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

    Neuronpedia

    INDEX
    Explanations

    names related to individuals, particularly those with the root "Rafa" or similar phonetic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auer
    -0.18
    icari
    -0.17
    HIR
    -0.16
    erde
    -0.16
    olia
    -0.15
    ë§Ŀ
    -0.15
    aney
    -0.15
    alue
    -0.15
    å°
    -0.14
     accessor
    -0.14
    POSITIVE LOGITS
    ael
    0.33
    ae
    0.18
    lesia
    0.17
    elson
    0.16
    cky
    0.16
    rchive
    0.16
    ique
    0.15
    oul
    0.15
    ĮĢ
    0.15
    elop
    0.15
    Act Density 0.006%

    No Known Activations