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

    Neuronpedia

    INDEX
    Explanations

    references to structures or components of documents and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isher
    -0.17
    ient
    -0.17
     triple
    -0.16
    ysz
    -0.15
     both
    -0.15
     tr
    -0.14
     coll
    -0.14
    ,
    -0.14
     land
    -0.14
    ael
    -0.14
    POSITIVE LOGITS
     four
    0.24
    five
    0.23
    four
    0.23
     five
    0.22
     ÑĩеÑĤÑĭ
    0.18
     пÑıÑĤÑĮ
    0.18
     bá»ijn
    0.18
     cuatro
    0.18
     vier
    0.17
     FOUR
    0.17
    Act Density 0.176%

    No Known Activations