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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and phrases indicating numbers and lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rosse
    -0.17
    ikip
    -0.17
     ragaz
    -0.15
     огÑĢа
    -0.15
    ksam
    -0.15
    .updateDynamic
    -0.15
    interop
    -0.14
    oup
    -0.14
    hol
    -0.14
    ائرة
    -0.14
    POSITIVE LOGITS
     respectively
    0.22
     etc
    0.20
    .
    0.17
    etc
    0.17
    ï¼Į以åıĬ
    0.17
     samt
    0.15
     ÑĤоÑīо
    0.15
     plus
    0.15
     ÙĪاÙĦتÙĬ
    0.15
     nor
    0.14
    Act Density 0.198%

    No Known Activations