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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions and schedule references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iert
    -0.14
     typical
    -0.14
    kir
    -0.14
    çĸ¾
    -0.14
    ament
    -0.14
    isin
    -0.14
     ков
    -0.14
    chet
    -0.13
    egen
    -0.13
    athon
    -0.13
    POSITIVE LOGITS
    ishi
    0.17
    ivas
    0.14
    .localization
    0.14
    çŃĭ
    0.14
     Brooks
    0.13
    getter
    0.13
    ça
    0.13
    ousse
    0.13
    obuf
    0.13
     """.
    0.13
    Act Density 0.032%

    No Known Activations