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

    Neuronpedia

    INDEX
    Explanations

    references to quality assurance and consistency in production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    ela
    -0.15
     intentional
    -0.15
    :
    -0.14
     both
    -0.14
    (strtolower
    -0.14
    2
    -0.14
    ands
    -0.14
     approximately
    -0.14
    1
    -0.14
    POSITIVE LOGITS
    æŁIJ
    0.26
     ÙħØ«ÙĦا
    0.26
     somebody
    0.19
     XYZ
    0.19
    say
    0.18
     suddenly
    0.18
     напÑĢимеÑĢ
    0.17
     Widgets
    0.17
    someone
    0.16
     someone
    0.16
    Act Density 0.544%

    No Known Activations