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

    Neuronpedia

    INDEX
    Explanations

    concepts related to inclusivity and opportunity for diverse groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okino
    -0.14
    arding
    -0.14
    755
    -0.14
    oger
    -0.14
     Seymour
    -0.14
     successive
    -0.13
     occasionally
    -0.13
    ynos
    -0.13
    ÙĨدÛĮ
    -0.13
     occasional
    -0.13
    POSITIVE LOGITS
     all
    0.43
    æīĢæľī
    0.43
     wszyst
    0.39
     semua
    0.39
    ãģĻãģ¹ãģ¦
    0.38
     every
    0.37
     모ëĵł
    0.36
     everything
    0.36
     вÑģеÑħ
    0.34
     everyone
    0.34
    Act Density 0.276%

    No Known Activations