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

    Neuronpedia

    INDEX
    Explanations

    code snippets or programming structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osu
    -0.15
    éra
    -0.14
     figura
    -0.14
    elan
    -0.14
     æ¾
    -0.13
    ired
    -0.13
    .lu
    -0.13
    ноÑģÑıÑĤ
    -0.13
    íĤ¬
    -0.12
    ï¼ĪæĺŃåĴĮ
    -0.12
    POSITIVE LOGITS
    which
    0.28
    and
    0.23
     Which
    0.23
    Which
    0.21
     And
    0.21
    And
    0.21
    where
    0.19
    or
    0.19
     which
    0.19
    then
    0.19
    Act Density 0.087%

    No Known Activations