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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific targeting or customization for certain applications or audiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesel
    -0.18
     far
    -0.16
     ga
    -0.15
    éo
    -0.15
    रण
    -0.15
     Og
    -0.15
    بس
    -0.14
    urate
    -0.14
    ECH
    -0.14
     ale
    -0.14
    POSITIVE LOGITS
     specifically
    0.17
    дÑı
    0.16
    ders
    0.16
    ÑĤин
    0.15
    specific
    0.15
    939
    0.15
    urtle
    0.15
     конкÑĢеÑĤ
    0.15
    968
    0.14
    rats
    0.14
    Act Density 0.063%

    No Known Activations