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

    Neuronpedia

    INDEX
    Explanations

    instances of speaking out or expressing opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.17
    ilter
    -0.16
    lemen
    -0.15
    ikon
    -0.15
    大家
    -0.15
    اءة
    -0.14
    kus
    -0.14
    ÐľÐŀ
    -0.14
    egr
    -0.14
    ieux
    -0.14
    POSITIVE LOGITS
    ylene
    0.16
    endar
    0.15
    ÑĮÑİ
    0.15
    otos
    0.14
    /WebAPI
    0.14
     Joshua
    0.14
    urança
    0.14
    ugar
    0.14
    aight
    0.14
    /tinyos
    0.14
    Act Density 0.008%

    No Known Activations