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

    Neuronpedia

    INDEX
    Explanations

    terms related to swearing or strong language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ialog
    -0.16
    rawler
    -0.15
    .epam
    -0.15
     Falcon
    -0.14
    CALE
    -0.14
    wan
    -0.13
    opic
    -0.13
    uke
    -0.13
    uration
    -0.13
    lex
    -0.13
    POSITIVE LOGITS
    auc
    0.15
    αιν
    0.15
    ADIUS
    0.15
    inand
    0.15
     GDK
    0.14
    reff
    0.14
    ÑĸннÑı
    0.14
    rou
    0.14
    handleRequest
    0.14
     Landing
    0.14
    Act Density 0.008%

    No Known Activations