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

    Neuronpedia

    INDEX
    Explanations

    high-frequency or significant terms or concepts related to evidence, challenges, or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    848
    -0.18
    ugg
    -0.17
    /*@
    -0.15
     Branch
    -0.15
    471
    -0.15
    eren
    -0.15
    lord
    -0.14
     Armour
    -0.14
    yyyy
    -0.14
    ova
    -0.14
    POSITIVE LOGITS
    ãģ¬
    0.18
    ayım
    0.15
    allery
    0.15
    querque
    0.14
    remen
    0.14
    axy
    0.14
    Nut
    0.14
    beros
    0.14
    å¯Ĵ
    0.14
    cbc
    0.13
    Act Density 0.024%

    No Known Activations