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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant amount or degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ð¡Ðł
    -0.16
    úa
    -0.14
    ulong
    -0.14
    /ay
    -0.14
    ç®
    -0.14
    antu
    -0.14
    oÄį
    -0.14
    .slim
    -0.14
     pa
    -0.14
     pack
    -0.14
    POSITIVE LOGITS
     Pier
    0.15
    rane
    0.15
    mia
    0.15
    Ïģαν
    0.14
    laus
    0.14
    κι
    0.14
    OfDay
    0.13
    å°½
    0.13
    erable
    0.13
     Preview
    0.13
    Act Density 0.002%

    No Known Activations