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

    Neuronpedia

    INDEX
    Explanations

    references to processes and actions in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elsewhere
    -0.15
     occasionally
    -0.14
     depending
    -0.14
    à¸ļาà¸ĩ
    -0.14
    849
    -0.14
     consecutive
    -0.13
    "Some
    -0.13
     sometimes
    -0.13
     successive
    -0.13
    depending
    -0.12
    POSITIVE LOGITS
    æīĢæľī
    0.53
     all
    0.50
     every
    0.46
    ãģĻãģ¹ãģ¦
    0.44
     wszyst
    0.44
     semua
    0.43
     모ëĵł
    0.43
     вÑģеÑħ
    0.42
     everything
    0.41
     tất
    0.38
    Act Density 0.325%

    No Known Activations