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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to cultural or societal contexts, especially concerning personal experiences or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AZY
    -0.18
    allet
    -0.16
    ]={↵
    -0.16
    itle
    -0.15
    andel
    -0.14
    phe
    -0.14
    ظÙĩ
    -0.14
    Äĩe
    -0.14
    cheng
    -0.14
    prak
    -0.14
    POSITIVE LOGITS
    argins
    0.15
    رÙĪÛĮ
    0.15
    Ñĥй
    0.14
    ober
    0.14
     Princip
    0.13
    aid
    0.13
    主
    0.13
    ãĤµãĥ¼
    0.12
     Banco
    0.12
     Fou
    0.12
    Act Density 0.024%

    No Known Activations