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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases that present a list or set of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ?><?
    -0.15
    Ùħبر
    -0.15
    åĨ²
    -0.14
    è¹
    -0.14
    auc
    -0.14
    oku
    -0.14
    uch
    -0.13
    ạ
    -0.13
    znik
    -0.13
    ÛĮØ´ÙĨ
    -0.13
    POSITIVE LOGITS
     five
    0.23
     some
    0.21
     suggestions
    0.19
     tips
    0.18
    five
    0.18
     quelques
    0.18
     three
    0.17
     four
    0.17
     six
    0.17
     suggested
    0.16
    Act Density 0.039%

    No Known Activations