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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional relationships or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engin
    -0.07
    unca
    -0.06
    unnel
    -0.06
    atted
    -0.06
    ouch
    -0.06
     everybody
    -0.06
    /loader
    -0.06
    /loading
    -0.06
     Something
    -0.05
    ouched
    -0.05
    POSITIVE LOGITS
     or
    0.24
    æĪĸ
    0.22
     или
    0.21
    æĪĸèĢħ
    0.20
     æĪĸ
    0.19
     hoặc
    0.19
     atau
    0.18
    /or
    0.18
     ÛĮا
    0.18
     nebo
    0.18
    Act Density 0.153%

    No Known Activations