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

    Neuronpedia

    INDEX
    Explanations

    instances of various relational and transactional terms within context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inati
    -0.17
     addCriterion
    -0.17
    cles
    -0.17
    etur
    -0.15
    ubits
    -0.15
    anzi
    -0.15
    translations
    -0.15
    oola
    -0.15
    UnderTest
    -0.14
    lisi
    -0.14
    POSITIVE LOGITS
     ÐĴики
    0.17
    ôn
    0.14
    azer
    0.14
    (^
    0.14
     default
    0.14
     Wel
    0.14
     пеÑĢемен
    0.14
    form
    0.13
     charter
    0.13
     ascend
    0.13
    Act Density 0.038%

    No Known Activations