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

    Neuronpedia

    INDEX
    Explanations

    references to social issues and community impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     firstly
    -0.23
     either
    -0.21
     Firstly
    -0.19
    æĹ¢
    -0.18
    either
    -0.18
    :
    -0.17
     nejen
    -0.17
    ãģ¾ãģļ
    -0.17
     både
    -0.17
     EITHER
    -0.17
    POSITIVE LOGITS
     consequ
    0.28
     importantly
    0.26
     subsequent
    0.26
     overall
    0.23
     subsequently
    0.22
     consequently
    0.22
     others
    0.21
    /or
    0.20
     other
    0.19
    overall
    0.19
    Act Density 1.479%

    No Known Activations