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

    Neuronpedia

    INDEX
    Explanations

    references to release timelines or availability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.16
     both
    -0.15
     Poss
    -0.15
    [
    -0.14
     poss
    -0.14
    eum
    -0.14
    unden
    -0.14
     pol
    -0.14
     Both
    -0.13
     wei
    -0.13
    POSITIVE LOGITS
    æĪĸèĢħ
    0.26
     или
    0.26
     hoặc
    0.24
     либо
    0.24
     oder
    0.23
     eller
    0.23
     atau
    0.23
     ÛĮا
    0.23
     æĪĸ
    0.23
     or
    0.22
    Act Density 0.008%

    No Known Activations