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

    Neuronpedia

    INDEX
    Explanations

    information about television shows, including updates and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atra
    -0.17
    itr
    -0.15
    trie
    -0.15
    ardin
    -0.15
    ortion
    -0.15
    abay
    -0.14
    lder
    -0.14
    errat
    -0.14
    ilers
    -0.14
    ugin
    -0.14
    POSITIVE LOGITS
    Îŀ
    0.16
     Kauf
    0.15
    âŁ
    0.14
    yar
    0.13
     ren
    0.13
    år
    0.13
    adden
    0.13
    ë§IJ
    0.13
     Hist
    0.13
     hen
    0.13
    Act Density 0.015%

    No Known Activations