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

    Neuronpedia

    INDEX
    Explanations

    elements related to rules and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     probably
    -0.17
     darn
    -0.15
     both
    -0.15
     Probably
    -0.14
     quite
    -0.14
     almost
    -0.14
    probably
    -0.14
     nearly
    -0.14
     much
    -0.14
     until
    -0.14
    POSITIVE LOGITS
    ï¼ĮåĪĻ
    0.27
     _______,
    0.22
     thì
    0.21
    ëĿ¼ëıĦ
    0.20
    æŁIJ
    0.19
    çļĦè¯Ŀ
    0.19
     maka
    0.18
    (any
    0.18
     varsa
    0.18
     nÃło
    0.18
    Act Density 0.447%

    No Known Activations