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

    Neuronpedia

    INDEX
    Explanations

    keywords that indicate significant actions, conditions, or roles related to varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     punct
    -0.15
     Finder
    -0.15
    .absolute
    -0.15
    ÑĸннÑı
    -0.14
    ÑĮÑİÑĤ
    -0.14
     Han
    -0.14
    [P
    -0.14
     Ports
    -0.14
     bolt
    -0.14
    Evaluator
    -0.14
    POSITIVE LOGITS
    elpers
    0.16
    Äįet
    0.16
    ady
    0.16
    ftar
    0.15
    .kr
    0.15
    mey
    0.15
    ár
    0.15
     è¶
    0.14
     Kes
    0.14
    à¸ĺรรม
    0.14
    Act Density 0.006%

    No Known Activations