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

    Neuronpedia

    INDEX
    Explanations

    instances of category labels and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beste
    -0.16
     Mature
    -0.15
    etur
    -0.15
     Dawn
    -0.14
    (åľŁ
    -0.14
    isin
    -0.14
    SES
    -0.14
    /documentation
    -0.13
    å¨
    -0.13
    assin
    -0.13
    POSITIVE LOGITS
    byname
    0.15
     íĽĦ기
    0.15
    oogle
    0.15
    asha
    0.15
    .dc
    0.14
    igos
    0.14
    esian
    0.14
    оже
    0.14
    Visibility
    0.13
    anghai
    0.13
    Act Density 0.017%

    No Known Activations