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

    Neuronpedia

    INDEX
    Explanations

    phrases marked by quotation marks or apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     اÙĪÙĨ
    -0.15
    åĪ»
    -0.14
    ido
    -0.14
    275
    -0.13
    bike
    -0.13
    ãĥ³ãĥĨãĤ£
    -0.13
    seau
    -0.13
    leton
    -0.13
    '=>['
    -0.13
     ìĿ´ìĸ´
    -0.13
    POSITIVE LOGITS
    ÏĨÏħ
    0.15
     Baum
    0.15
     Wagner
    0.15
    éijij
    0.14
    acock
    0.14
    eck
    0.14
    encias
    0.14
     arts
    0.13
    rescia
    0.13
     Iv
    0.13
    Act Density 0.114%

    No Known Activations